def fit_binary(self, data_instances, validate_data):
self._abnormal_detection(data_instances)
validation_strategy = self.init_validation_strategy(
data_instances, validate_data)
LOGGER.debug(
f"MODEL_STEP Start fin_binary, data count: {data_instances.count()}"
)
self.header = self.get_header(data_instances)
self.cipher_operator = self.cipher.gen_paillier_cipher_operator()
self.batch_generator.initialize_batch_generator(data_instances)
self.gradient_loss_operator.set_total_batch_nums(
self.batch_generator.batch_nums)
self.encrypted_calculator = [
EncryptModeCalculator(
self.cipher_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate)
for _ in range(self.batch_generator.batch_nums)
]
LOGGER.info("Start initialize model.")
model_shape = self.get_features_shape(data_instances)
if self.init_param_obj.fit_intercept:
self.init_param_obj.fit_intercept = False
w = self.initializer.init_model(model_shape,
init_params=self.init_param_obj)
LOGGER.debug("model_shape: {}, w shape: {}, w: {}".format(
model_shape, w.shape, w))
self.model_weights = LinearModelWeights(
w, fit_intercept=self.init_param_obj.fit_intercept)
while self.n_iter_ < self.max_iter:
LOGGER.info("iter:" + str(self.n_iter_))
batch_data_generator = self.batch_generator.generate_batch_data()
batch_index = 0
self.optimizer.set_iters(self.n_iter_)
for batch_data in batch_data_generator:
# transforms features of raw input 'batch_data_inst' into more representative features 'batch_feat_inst'
batch_feat_inst = self.transform(batch_data)
LOGGER.debug(
f"MODEL_STEP In Batch {batch_index}, batch data count: {batch_feat_inst.count()}"
)
optim_host_gradient, fore_gradient = self.gradient_loss_operator.compute_gradient_procedure(
batch_feat_inst, self.encrypted_calculator,
self.model_weights, self.optimizer, self.n_iter_,
batch_index)
LOGGER.debug(
'optim_host_gradient: {}'.format(optim_host_gradient))
training_info = {
"iteration": self.n_iter_,
"batch_index": batch_index
}
self.update_local_model(fore_gradient, data_instances,
self.model_weights.coef_,
**training_info)
self.gradient_loss_operator.compute_loss(
self.model_weights, self.optimizer, self.n_iter_,
batch_index, self.cipher_operator)
self.model_weights = self.optimizer.update_model(
self.model_weights, optim_host_gradient)
batch_index += 1
self.is_converged = self.converge_procedure.sync_converge_info(
suffix=(self.n_iter_, ))
LOGGER.info("Get is_converged flag from arbiter:{}".format(
self.is_converged))
validation_strategy.validate(self, self.n_iter_)
self.n_iter_ += 1
LOGGER.info("iter: {}, is_converged: {}".format(
self.n_iter_, self.is_converged))
if self.is_converged:
break
LOGGER.debug("Final lr weights: {}".format(self.model_weights.unboxed))
def fit(self, data_instances, validate_data=None):
"""
Train poisson model of role guest
Parameters
----------
data_instances: DTable of Instance, input data
"""
LOGGER.info("Enter hetero_poisson_guest fit")
self._abnormal_detection(data_instances)
self.header = copy.deepcopy(self.get_header(data_instances))
validation_strategy = self.init_validation_strategy(data_instances, validate_data)
self.exposure_index = self.get_exposure_index(self.header, self.exposure_colname)
if self.exposure_index > -1:
self.header.pop(self.exposure_index)
LOGGER.info("expsoure provided at Guest, colname is {}".format(self.exposure_colname))
exposure = data_instances.mapValues(lambda v: self.load_exposure(v))
data_instances = data_instances.mapValues(lambda v: self.load_instance(v))
self.cipher_operator = self.cipher.gen_paillier_cipher_operator()
LOGGER.info("Generate mini-batch from input data")
self.batch_generator.initialize_batch_generator(data_instances, self.batch_size)
self.encrypted_calculator = [EncryptModeCalculator(self.cipher_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate) for _
in range(self.batch_generator.batch_nums)]
LOGGER.info("Start initialize model.")
LOGGER.info("fit_intercept:{}".format(self.init_param_obj.fit_intercept))
model_shape = self.get_features_shape(data_instances)
w = self.initializer.init_model(model_shape, init_params=self.init_param_obj)
self.model_weights = LinearModelWeights(w, fit_intercept=self.fit_intercept)
while self.n_iter_ < self.max_iter:
LOGGER.info("iter:{}".format(self.n_iter_))
# each iter will get the same batch_data_generator
batch_data_generator = self.batch_generator.generate_batch_data()
self.optimizer.set_iters(self.n_iter_)
batch_index = 0
for batch_data in batch_data_generator:
# transforms features of raw input 'batch_data_inst' into more representative features 'batch_feat_inst'
batch_feat_inst = self.transform(batch_data)
# compute offset of this batch
batch_offset = exposure.join(batch_feat_inst, lambda ei, d: self.safe_log(ei))
# Start gradient procedure
optimized_gradient, _, _ = self.gradient_loss_operator.compute_gradient_procedure(
batch_feat_inst,
self.encrypted_calculator,
self.model_weights,
self.optimizer,
self.n_iter_,
batch_index,
batch_offset
)
LOGGER.debug("iteration:{} Guest's gradient: {}".format(self.n_iter_, optimized_gradient))
loss_norm = self.optimizer.loss_norm(self.model_weights)
self.gradient_loss_operator.compute_loss(data_instances, self.model_weights, self.n_iter_,
batch_index, batch_offset, loss_norm)
self.model_weights = self.optimizer.update_model(self.model_weights, optimized_gradient)
batch_index += 1
self.is_converged = self.converge_procedure.sync_converge_info(suffix=(self.n_iter_,))
LOGGER.info("iter: {}, is_converged: {}".format(self.n_iter_, self.is_converged))
validation_strategy.validate(self, self.n_iter_)
self.n_iter_ += 1
if self.is_converged:
break
def fit_binary(self, data_instances, validate_data=None):
LOGGER.info("Enter hetero_fm_guest fit")
self.header = self.get_header(data_instances)
validation_strategy = self.init_validation_strategy(data_instances, validate_data)
data_instances = data_instances.mapValues(HeteroFMGuest.load_data)
LOGGER.debug(f"MODEL_STEP After load data, data count: {data_instances.count()}")
self.cipher_operator = self.cipher.gen_paillier_cipher_operator()
LOGGER.info("Generate mini-batch from input data")
self.batch_generator.initialize_batch_generator(data_instances, self.batch_size)
self.encrypted_calculator = [EncryptModeCalculator(self.cipher_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate) for _
in range(self.batch_generator.batch_nums)]
LOGGER.info("Start initialize model.")
LOGGER.info("fit_intercept:{}".format(self.init_param_obj.fit_intercept))
model_shape = self.get_features_shape(data_instances)
# intercept is initialized within FactorizationMachineWeights.
# Skip initializer's intercept part.
fit_intercept = False
if self.init_param_obj.fit_intercept:
fit_intercept = True
self.init_param_obj.fit_intercept = False
w_ = self.initializer.init_model(model_shape, init_params=self.init_param_obj)
embed_ = np.random.normal(scale=1 / np.sqrt(self.init_param_obj.embed_size),
size=(model_shape, self.init_param_obj.embed_size))
self.model_weights = \
FactorizationMachineWeights(w_, embed_, fit_intercept=fit_intercept)
while self.n_iter_ < self.max_iter:
LOGGER.info("iter:{}".format(self.n_iter_))
batch_data_generator = self.batch_generator.generate_batch_data()
self.optimizer.set_iters(self.n_iter_)
batch_index = 0
for batch_data in batch_data_generator:
LOGGER.debug(f"MODEL_STEP In Batch {batch_index}, batch data count: {batch_data.count()}")
# Start gradient procedure
LOGGER.debug("iter: {}, before compute gradient, data count: {}".format(self.n_iter_,
batch_data.count()))
# optim_guest_gradient, fore_gradient, host_forwards = self.gradient_loss_operator. \
optim_guest_gradient, fore_gradient = self.gradient_loss_operator. \
compute_gradient_procedure(
batch_data,
self.encrypted_calculator,
self.model_weights,
self.optimizer,
self.n_iter_,
batch_index
)
LOGGER.debug('optim_guest_gradient: {}'.format(optim_guest_gradient))
loss_norm = self.optimizer.loss_norm(self.model_weights)
self.gradient_loss_operator.compute_loss(data_instances, self.n_iter_, batch_index, loss_norm)
# clip gradient
if self.model_param.clip_gradient and self.model_param.clip_gradient > 0:
optim_guest_gradient = np.maximum(optim_guest_gradient, -self.model_param.clip_gradient)
optim_guest_gradient = np.minimum(optim_guest_gradient, self.model_param.clip_gradient)
_model_weights = self.optimizer.update_model(self.model_weights, optim_guest_gradient)
self.model_weights.update(_model_weights)
batch_index += 1
LOGGER.debug("fm_weight, iters: {}, update_model: {}".format(self.n_iter_, self.model_weights.unboxed))
self.is_converged = self.converge_procedure.sync_converge_info(suffix=(self.n_iter_,))
LOGGER.info("iter: {}, is_converged: {}".format(self.n_iter_, self.is_converged))
validation_strategy.validate(self, self.n_iter_)
self.n_iter_ += 1
if self.is_converged:
break
LOGGER.debug("Final fm weights: {}".format(self.model_weights.unboxed))
def fit_binary(self, data_instances, validate_data=None):
LOGGER.info("Enter hetero_lr_guest fit")
self.header = self.get_header(data_instances)
self.validation_strategy = self.init_validation_strategy(
data_instances, validate_data)
data_instances = data_instances.mapValues(HeteroLRGuest.load_data)
LOGGER.debug(
f"MODEL_STEP After load data, data count: {data_instances.count()}"
)
self.cipher_operator = self.cipher.gen_paillier_cipher_operator()
LOGGER.info("Generate mini-batch from input data")
self.batch_generator.initialize_batch_generator(
data_instances, self.batch_size)
self.gradient_loss_operator.set_total_batch_nums(
self.batch_generator.batch_nums)
self.encrypted_calculator = [
EncryptModeCalculator(
self.cipher_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate)
for _ in range(self.batch_generator.batch_nums)
]
LOGGER.info("Start initialize model.")
LOGGER.info("fit_intercept:{}".format(
self.init_param_obj.fit_intercept))
model_shape = self.get_features_shape(data_instances)
w = self.initializer.init_model(model_shape,
init_params=self.init_param_obj)
self.model_weights = LinearModelWeights(
w, fit_intercept=self.fit_intercept)
while self.n_iter_ < self.max_iter:
LOGGER.info("iter:{}".format(self.n_iter_))
batch_data_generator = self.batch_generator.generate_batch_data()
self.optimizer.set_iters(self.n_iter_)
batch_index = 0
for batch_data in batch_data_generator:
# transforms features of raw input 'batch_data_inst' into more representative features 'batch_feat_inst'
batch_feat_inst = batch_data
# LOGGER.debug(f"MODEL_STEP In Batch {batch_index}, batch data count: {batch_feat_inst.count()}")
# Start gradient procedure
LOGGER.debug(
"iter: {}, before compute gradient, data count: {}".format(
self.n_iter_, batch_feat_inst.count()))
optim_guest_gradient = self.gradient_loss_operator.compute_gradient_procedure(
batch_feat_inst, self.encrypted_calculator,
self.model_weights, self.optimizer, self.n_iter_,
batch_index)
# LOGGER.debug('optim_guest_gradient: {}'.format(optim_guest_gradient))
# training_info = {"iteration": self.n_iter_, "batch_index": batch_index}
# self.update_local_model(fore_gradient, data_instances, self.model_weights.coef_, **training_info)
loss_norm = self.optimizer.loss_norm(self.model_weights)
self.gradient_loss_operator.compute_loss(
data_instances, self.model_weights, self.n_iter_,
batch_index, loss_norm)
self.model_weights = self.optimizer.update_model(
self.model_weights, optim_guest_gradient)
batch_index += 1
# LOGGER.debug("lr_weight, iters: {}, update_model: {}".format(self.n_iter_, self.model_weights.unboxed))
self.is_converged = self.converge_procedure.sync_converge_info(
suffix=(self.n_iter_, ))
LOGGER.info("iter: {}, is_converged: {}".format(
self.n_iter_, self.is_converged))
if self.validation_strategy:
LOGGER.debug('LR guest running validation')
self.validation_strategy.validate(self, self.n_iter_)
if self.validation_strategy.need_stop():
LOGGER.debug('early stopping triggered')
break
self.n_iter_ += 1
if self.is_converged:
break
if self.validation_strategy and self.validation_strategy.has_saved_best_model(
):
self.load_model(self.validation_strategy.cur_best_model)
self.set_summary(self.get_model_summary())
def fit(self, data_instances):
"""
Train lr model of role guest
Parameters
----------
data_instances: DTable of Instance, input data
"""
LOGGER.info("Enter hetero_lr_guest fit")
self._abnormal_detection(data_instances)
self.header = self.get_header(data_instances)
data_instances = data_instances.mapValues(HeteroLRGuest.load_data)
# 获得密钥
public_key = federation.get(
name=self.transfer_variable.paillier_pubkey.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.paillier_pubkey),
idx=0)
LOGGER.info("Get public_key from arbiter:{}".format(public_key))
self.encrypt_operator.set_public_key(public_key)
LOGGER.info("Generate mini-batch from input data")
mini_batch_obj = MiniBatch(data_instances, batch_size=self.batch_size)
batch_num = mini_batch_obj.batch_nums
if self.batch_size == -1:
LOGGER.info(
"batch size is -1, set it to the number of data in data_instances"
)
self.batch_size = data_instances.count()
batch_info = {"batch_size": self.batch_size, "batch_num": batch_num}
LOGGER.info("batch_info:{}".format(batch_info))
federation.remote(batch_info,
name=self.transfer_variable.batch_info.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.batch_info),
role=consts.HOST,
idx=0)
LOGGER.info("Remote batch_info to Host")
federation.remote(batch_info,
name=self.transfer_variable.batch_info.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.batch_info),
role=consts.ARBITER,
idx=0)
LOGGER.info("Remote batch_info to Arbiter")
self.encrypted_calculator = [
EncryptModeCalculator(
self.encrypt_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate)
for _ in range(batch_num)
]
LOGGER.info("Start initialize model.")
LOGGER.info("fit_intercept:{}".format(
self.init_param_obj.fit_intercept))
model_shape = self.get_features_shape(data_instances)
weight = self.initializer.init_model(model_shape,
init_params=self.init_param_obj)
if self.init_param_obj.fit_intercept is True:
self.coef_ = weight[:-1]
self.intercept_ = weight[-1]
else:
self.coef_ = weight
is_send_all_batch_index = False
self.n_iter_ = 0
index_data_inst_map = {}
while self.n_iter_ < self.max_iter:
LOGGER.info("iter:{}".format(self.n_iter_))
# each iter will get the same batch_data_generator
batch_data_generator = mini_batch_obj.mini_batch_data_generator(
result='index')
batch_index = 0
for batch_data_index in batch_data_generator:
LOGGER.info("batch:{}".format(batch_index))
if not is_send_all_batch_index:
LOGGER.info("remote mini-batch index to Host")
federation.remote(
batch_data_index,
name=self.transfer_variable.batch_data_index.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.batch_data_index,
self.n_iter_, batch_index),
role=consts.HOST,
idx=0)
if batch_index >= mini_batch_obj.batch_nums - 1:
is_send_all_batch_index = True
# Get mini-batch train data
if len(index_data_inst_map) < batch_num:
batch_data_inst = data_instances.join(
batch_data_index, lambda data_inst, index: data_inst)
index_data_inst_map[batch_index] = batch_data_inst
else:
batch_data_inst = index_data_inst_map[batch_index]
# transforms features of raw input 'batch_data_inst' into more representative features 'batch_feat_inst'
batch_feat_inst = self.transform(batch_data_inst)
# guest/host forward
self.compute_forward(batch_feat_inst, self.coef_,
self.intercept_, batch_index)
host_forward = federation.get(
name=self.transfer_variable.host_forward_dict.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_forward_dict, self.n_iter_,
batch_index),
idx=0)
LOGGER.info("Get host_forward from host")
aggregate_forward_res = self.aggregate_forward(host_forward)
en_aggregate_wx = aggregate_forward_res.mapValues(
lambda v: v[0])
en_aggregate_wx_square = aggregate_forward_res.mapValues(
lambda v: v[1])
# compute [[d]]
if self.gradient_operator is None:
self.gradient_operator = HeteroLogisticGradient(
self.encrypt_operator)
fore_gradient = self.gradient_operator.compute_fore_gradient(
batch_feat_inst, en_aggregate_wx)
federation.remote(
fore_gradient,
name=self.transfer_variable.fore_gradient.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.fore_gradient, self.n_iter_,
batch_index),
role=consts.HOST,
idx=0)
LOGGER.info("Remote fore_gradient to Host")
# compute guest gradient and loss
guest_gradient, loss = self.gradient_operator.compute_gradient_and_loss(
batch_feat_inst, fore_gradient, en_aggregate_wx,
en_aggregate_wx_square, self.fit_intercept)
# loss regulation if necessary
if self.updater is not None:
guest_loss_regular = self.updater.loss_norm(self.coef_)
loss += self.encrypt_operator.encrypt(guest_loss_regular)
federation.remote(
guest_gradient,
name=self.transfer_variable.guest_gradient.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.guest_gradient, self.n_iter_,
batch_index),
role=consts.ARBITER,
idx=0)
LOGGER.info("Remote guest_gradient to arbiter")
optim_guest_gradient = federation.get(
name=self.transfer_variable.guest_optim_gradient.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.guest_optim_gradient,
self.n_iter_, batch_index),
idx=0)
LOGGER.info("Get optim_guest_gradient from arbiter")
# update model
LOGGER.info("update_model")
self.update_model(optim_guest_gradient)
# update local model that transforms features of raw input 'batch_data_inst'
training_info = {
"iteration": self.n_iter_,
"batch_index": batch_index
}
self.update_local_model(fore_gradient, batch_data_inst,
self.coef_, **training_info)
# Get loss regulation from Host if regulation is set
if self.updater is not None:
en_host_loss_regular = federation.get(
name=self.transfer_variable.host_loss_regular.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_loss_regular,
self.n_iter_, batch_index),
idx=0)
LOGGER.info("Get host_loss_regular from Host")
loss += en_host_loss_regular
federation.remote(
loss,
name=self.transfer_variable.loss.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.loss, self.n_iter_,
batch_index),
role=consts.ARBITER,
idx=0)
LOGGER.info("Remote loss to arbiter")
# is converge of loss in arbiter
batch_index += 1
# temporary resource recovery and will be removed in the future
rubbish_list = [
host_forward, aggregate_forward_res, en_aggregate_wx,
en_aggregate_wx_square, fore_gradient, self.guest_forward
]
rubbish_clear(rubbish_list)
is_stopped = federation.get(
name=self.transfer_variable.is_stopped.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.is_stopped, self.n_iter_,
batch_index),
idx=0)
LOGGER.info("Get is_stop flag from arbiter:{}".format(is_stopped))
self.n_iter_ += 1
if is_stopped:
LOGGER.info(
"Get stop signal from arbiter, model is converged, iter:{}"
.format(self.n_iter_))
break
LOGGER.info("Reach max iter {}, train model finish!".format(
self.max_iter))
def fit(self,
data_instances,
node2id,
local_instances=None,
common_nodes=None):
"""
Train node embedding for role guest
Parameters
----------
data_instances: DTable of target node and label, input data
node2id: a dict which can map node name to id
"""
LOGGER.info("samples number:{}".format(data_instances.count()))
LOGGER.info("Enter network embedding procedure:")
self.n_node = len(node2id)
LOGGER.info("Bank A has {} nodes".format(self.n_node))
data_instances = data_instances.mapValues(HeteroNEGuest.load_data)
LOGGER.info("Transform input data to train instance")
public_key = federation.get(
name=self.transfer_variable.paillier_pubkey.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.paillier_pubkey),
idx=0)
LOGGER.info("Get public_key from arbiter:{}".format(public_key))
self.encrypt_operator.set_public_key(public_key)
# hetero network embedding
LOGGER.info("Generate mini-batch from input data")
mini_batch_obj = MiniBatch(data_instances, batch_size=self.batch_size)
batch_num = mini_batch_obj.batch_nums
LOGGER.info("samples number:{}".format(data_instances.count()))
if self.batch_size == -1:
LOGGER.info(
"batch size is -1, set it to the number of data in data_instances"
)
self.batch_size = data_instances.count()
##############
# horizontal federated learning
LOGGER.info("Generate mini-batch for local instances in guest")
mini_batch_obj_local = MiniBatch(local_instances,
batch_size=self.batch_size)
local_batch_num = mini_batch_obj_local.batch_nums
common_node_instances = eggroll.parallelize(
((node, node) for node in common_nodes),
include_key=True,
name='common_nodes')
##############
batch_info = {'batch_size': self.batch_size, "batch_num": batch_num}
LOGGER.info("batch_info:{}".format(batch_info))
federation.remote(batch_info,
name=self.transfer_variable.batch_info.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.batch_info),
role=consts.HOST,
idx=0)
LOGGER.info("Remote batch_info to Host")
federation.remote(batch_info,
name=self.transfer_variable.batch_info.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.batch_info),
role=consts.ARBITER,
idx=0)
LOGGER.info("Remote batch_info to Arbiter")
self.encrypted_calculator = [
EncryptModeCalculator(
self.encrypt_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate)
for _ in range(batch_num)
]
LOGGER.info("Start initialize model.")
self.embedding_ = self.initializer.init_model((self.n_node, self.dim),
self.init_param_obj)
LOGGER.info("Embedding shape={}".format(self.embedding_.shape))
is_send_all_batch_index = False
self.n_iter_ = 0
index_data_inst_map = {}
while self.n_iter_ < self.max_iter:
LOGGER.info("iter:{}".format(self.n_iter_))
#################
local_batch_data_generator = mini_batch_obj_local.mini_batch_data_generator(
)
total_loss = 0
local_batch_num = 0
LOGGER.info("Enter the horizontally federated learning procedure:")
for local_batch_data in local_batch_data_generator:
n = local_batch_data.count()
#LOGGER.info("Local batch data count:{}".format(n))
E_Y = self.compute_local_embedding(local_batch_data,
self.embedding_, node2id)
local_grads_e1, local_grads_e2, local_loss = self.local_gradient_operator.compute(
E_Y, 'E_1')
local_grads_e1 = local_grads_e1.mapValues(
lambda g: self.local_optimizer.apply_gradients(g / n))
local_grads_e2 = local_grads_e2.mapValues(
lambda g: self.local_optimizer.apply_gradients(g / n))
e1id_join_grads = local_batch_data.join(
local_grads_e1, lambda v, g: (node2id[v[0]], g))
e2id_join_grads = local_batch_data.join(
local_grads_e2, lambda v, g: (node2id[v[1]], g))
self.update_model(e1id_join_grads)
self.update_model(e2id_join_grads)
local_loss = local_loss / n
local_batch_num += 1
total_loss += local_loss
#LOGGER.info("gradient count:{}".format(e1id_join_grads.count()))
guest_common_embedding = common_node_instances.mapValues(
lambda node: self.embedding_[node2id[node]])
federation.remote(
guest_common_embedding,
name=self.transfer_variable.guest_common_embedding.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.guest_common_embedding,
self.n_iter_, 0),
role=consts.ARBITER,
idx=0)
LOGGER.info("Remote the embedding of common node to arbiter!")
common_embedding = federation.get(
name=self.transfer_variable.common_embedding.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.common_embedding, self.n_iter_, 0),
idx=0)
LOGGER.info(
"Get the aggregated embedding of common node from arbiter!")
self.update_common_nodes(common_embedding, common_nodes, node2id)
total_loss /= local_batch_num
LOGGER.info(
"Iter {}, horizontally feaderated learning loss: {}".format(
self.n_iter_, total_loss))
#################
# verticallly feaderated learning
# each iter will get the same batch_data_generator
LOGGER.info("Enter the vertically federated learning:")
batch_data_generator = mini_batch_obj.mini_batch_data_generator(
result='index')
batch_index = 0
for batch_data_index in batch_data_generator:
LOGGER.info("batch:{}".format(batch_index))
# only need to send one times
if not is_send_all_batch_index:
LOGGER.info("remote mini-batch index to Host")
federation.remote(
batch_data_index,
name=self.transfer_variable.batch_data_index.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.batch_data_index,
self.n_iter_, batch_index),
role=consts.HOST,
idx=0)
if batch_index >= mini_batch_obj.batch_nums - 1:
is_send_all_batch_index = True
# in order to avoid joining in next iteration
# Get mini-batch train data
if len(index_data_inst_map) < batch_num:
batch_data_inst = data_instances.join(
batch_data_index, lambda data_inst, index: data_inst)
index_data_inst_map[batch_index] = batch_data_inst
else:
batch_data_inst = index_data_inst_map[batch_index]
# For inductive learning: transform node attributes to node embedding
# self.transform(batch_data_inst)
self.guest_forward = self.compute_forward(
batch_data_inst, self.embedding_, node2id, batch_index)
host_forward = federation.get(
name=self.transfer_variable.host_forward_dict.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_forward_dict, self.n_iter_,
batch_index),
idx=0)
LOGGER.info("Get host_forward from host")
aggregate_forward_res = self.aggregate_forward(host_forward)
en_aggregate_ee = aggregate_forward_res.mapValues(
lambda v: v[0])
en_aggregate_ee_square = aggregate_forward_res.mapValues(
lambda v: v[1])
# compute [[d]]
if self.gradient_operator is None:
self.gradient_operator = HeteroNetworkEmbeddingGradient(
self.encrypt_operator)
fore_gradient = self.gradient_operator.compute_fore_gradient(
batch_data_inst, en_aggregate_ee)
host_gradient = self.gradient_operator.compute_gradient(
self.guest_forward.mapValues(
lambda v: Instance(features=v[1])), fore_gradient)
federation.remote(
host_gradient,
name=self.transfer_variable.host_gradient.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_gradient, self.n_iter_,
batch_index),
role=consts.ARBITER,
idx=0)
LOGGER.info("Remote host_gradient to arbiter")
composed_data_inst = host_forward.join(
batch_data_inst,
lambda hf, d: Instance(features=hf[1], label=d.label))
guest_gradient, loss = self.gradient_operator.compute_gradient_and_loss(
composed_data_inst, fore_gradient, en_aggregate_ee,
en_aggregate_ee_square)
federation.remote(
guest_gradient,
name=self.transfer_variable.guest_gradient.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.guest_gradient, self.n_iter_,
batch_index),
role=consts.ARBITER,
idx=0)
LOGGER.info("Remote guest_gradient to arbiter")
optim_guest_gradient = federation.get(
name=self.transfer_variable.guest_optim_gradient.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.guest_optim_gradient,
self.n_iter_, batch_index),
idx=0)
LOGGER.info("Get optim_guest_gradient from arbiter")
# update node embedding
LOGGER.info("Update node embedding")
nodeid_join_gradient = batch_data_inst.join(
optim_guest_gradient, lambda instance, gradient:
(node2id[instance.features], gradient))
self.update_model(nodeid_join_gradient)
# update local model that transform attribute to node embedding
training_info = {
'iteration': self.n_iter_,
'batch_index': batch_index
}
self.update_local_model(fore_gradient, batch_data_inst,
self.embedding_, **training_info)
# loss need to be encrypted !!!!!!
federation.remote(
loss,
name=self.transfer_variable.loss.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.loss, self.n_iter_,
batch_index),
role=consts.ARBITER,
idx=0)
LOGGER.info("Remote loss to arbiter")
# is converge of loss in arbiter
batch_index += 1
# remove temporary resource
rubbish_list = [
host_forward, aggregate_forward_res, en_aggregate_ee,
en_aggregate_ee_square, fore_gradient, self.guest_forward
]
rubbish_clear(rubbish_list)
##########
guest_common_embedding = common_node_instances.mapValues(
lambda node: self.embedding_[node2id[node]])
federation.remote(
guest_common_embedding,
name=self.transfer_variable.guest_common_embedding.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.guest_common_embedding,
self.n_iter_, 1),
role=consts.ARBITER,
idx=0)
common_embedding = federation.get(
name=self.transfer_variable.common_embedding.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.common_embedding, self.n_iter_, 1),
idx=0)
self.update_common_nodes(common_embedding, common_nodes, node2id)
##########
is_stopped = federation.get(
name=self.transfer_variable.is_stopped.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.is_stopped, self.n_iter_),
idx=0)
LOGGER.info("Get is_stop flag from arbiter:{}".format(is_stopped))
self.n_iter_ += 1
if is_stopped:
LOGGER.info(
"Get stop signal from arbiter, model is converged, iter:{}"
.format(self.n_iter_))
break
embedding_table = eggroll.table(name='guest',
namespace='node_embedding',
partition=10)
id2node = dict(zip(node2id.values(), node2id.keys()))
for id, embedding in enumerate(self.embedding_):
embedding_table.put(id2node[id], embedding)
embedding_table.save_as(name='guest',
namespace='node_embedding',
partition=10)
LOGGER.info("Reach max iter {}, train model finish!".format(
self.max_iter))
def fit(self, data_instances, validate_data=None):
"""
Train linear regression model of role host
Parameters
----------
data_instances: Table of Instance, input data
"""
LOGGER.info("Enter hetero_linR host")
self._abnormal_detection(data_instances)
self.header = self.get_header(data_instances)
self.callback_list.on_train_begin(data_instances, validate_data)
self.cipher_operator = self.cipher.gen_paillier_cipher_operator()
if self.transfer_variable.use_async.get(idx=0):
LOGGER.debug(f"set_use_async")
self.gradient_loss_operator.set_use_async()
self.batch_generator.initialize_batch_generator(data_instances)
self.gradient_loss_operator.set_total_batch_nums(self.batch_generator.batch_nums)
self.encrypted_calculator = [EncryptModeCalculator(self.cipher_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate) for _
in range(self.batch_generator.batch_nums)]
LOGGER.info("Start initialize model.")
model_shape = self.get_features_shape(data_instances)
if self.init_param_obj.fit_intercept:
self.init_param_obj.fit_intercept = False
if not self.component_properties.is_warm_start:
w = self.initializer.init_model(model_shape, init_params=self.init_param_obj)
self.model_weights = LinearModelWeights(w, fit_intercept=self.fit_intercept, raise_overflow_error=False)
else:
self.callback_warm_start_init_iter(self.n_iter_)
while self.n_iter_ < self.max_iter:
self.callback_list.on_epoch_begin(self.n_iter_)
LOGGER.info("iter:" + str(self.n_iter_))
self.optimizer.set_iters(self.n_iter_)
batch_data_generator = self.batch_generator.generate_batch_data()
batch_index = 0
for batch_data in batch_data_generator:
optim_host_gradient = self.gradient_loss_operator.compute_gradient_procedure(
batch_data,
self.encrypted_calculator,
self.model_weights,
self.optimizer,
self.n_iter_,
batch_index)
self.gradient_loss_operator.compute_loss(self.model_weights, self.optimizer, self.n_iter_, batch_index,
self.cipher_operator)
self.model_weights = self.optimizer.update_model(self.model_weights, optim_host_gradient)
batch_index += 1
self.is_converged = self.converge_procedure.sync_converge_info(suffix=(self.n_iter_,))
LOGGER.info("Get is_converged flag from arbiter:{}".format(self.is_converged))
self.callback_list.on_epoch_end(self.n_iter_)
self.n_iter_ += 1
if self.stop_training:
break
LOGGER.info("iter: {}, is_converged: {}".format(self.n_iter_, self.is_converged))
if self.is_converged:
break
self.callback_list.on_train_end()
self.set_summary(self.get_model_summary())
def fit(self,
data_instances,
node2id,
local_instances=None,
common_nodes=None):
"""
Train ne model pf role host
Parameters
----------
data_instances: Dtable of anchor node, input data
"""
LOGGER.info("Enter hetero_ne host")
self.n_node = len(node2id)
LOGGER.info("Host party has {} nodes".format(self.n_node))
data_instances = data_instances.mapValues(HeteroNEHost.load_data)
LOGGER.info("Transform input data to train instance")
public_key = federation.get(
name=self.transfer_variable.paillier_pubkey.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.paillier_pubkey),
idx=0)
LOGGER.info("Get Publick key from arbiter:{}".format(public_key))
self.encrypt_operator.set_public_key(public_key)
##############
# horizontal federated learning
LOGGER.info("Generate mini-batch for local instances in guest")
mini_batch_obj_local = MiniBatch(local_instances,
batch_size=self.batch_size)
common_node_instances = eggroll.parallelize(
((node, node) for node in common_nodes),
include_key=True,
name='common_nodes')
##############
batch_info = federation.get(
name=self.transfer_variable.batch_info.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.batch_info),
idx=0)
LOGGER.info("Get batch_info from guest: {}".format(batch_info))
self.batch_size = batch_info['batch_size']
self.batch_num = batch_info['batch_num']
if self.batch_size < consts.MIN_BATCH_SIZE and self.batch_size != -1:
raise ValueError(
"Batch size get from guest should not less than 10, except -1, batch_size is {}"
.format(self.batch_size))
self.encrypted_calculator = [
EncryptModeCalculator(
self.encrypt_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate)
for _ in range(self.batch_num)
]
LOGGER.info("Start initilize model.")
self.embedding_ = self.initializer.init_model((self.n_node, self.dim),
self.init_param_obj)
self.n_iter_ = 0
index_data_inst_map = {}
while self.n_iter_ < self.max_iter:
LOGGER.info("iter: {}".format(self.n_iter_))
#################
local_batch_data_generator = mini_batch_obj_local.mini_batch_data_generator(
)
total_loss = 0
local_batch_num = 0
LOGGER.info("Horizontally learning")
for local_batch_data in local_batch_data_generator:
n = local_batch_data.count()
LOGGER.info("Local batch data count:{}".format(n))
E_Y = self.compute_local_embedding(local_batch_data,
self.embedding_, node2id)
local_grads_e1, local_grads_e2, local_loss = self.local_gradient_operator.compute(
E_Y, 'E_1')
local_grads_e1 = local_grads_e1.mapValues(
lambda g: self.local_optimizer.apply_gradients(g / n))
local_grads_e2 = local_grads_e2.mapValues(
lambda g: self.local_optimizer.apply_gradients(g / n))
e1id_join_grads = local_batch_data.join(
local_grads_e1, lambda v, g: (node2id[v[0]], g))
e2id_join_grads = local_batch_data.join(
local_grads_e2, lambda v, g: (node2id[v[1]], g))
self.update_model(e1id_join_grads)
self.update_model(e2id_join_grads)
local_loss = local_loss / n
local_batch_num += 1
total_loss += local_loss
LOGGER.info("gradient count:{}".format(
e1id_join_grads.count()))
host_common_embedding = common_node_instances.mapValues(
lambda node: self.embedding_[node2id[node]])
federation.remote(
host_common_embedding,
name=self.transfer_variable.host_common_embedding.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_common_embedding, self.n_iter_,
0),
role=consts.ARBITER,
idx=0)
common_embedding = federation.get(
name=self.transfer_variable.common_embedding.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.common_embedding, self.n_iter_, 0),
idx=0)
self.update_common_nodes(common_embedding, common_nodes, node2id)
total_loss /= local_batch_num
LOGGER.info("Iter {}, Local loss: {}".format(
self.n_iter_, total_loss))
batch_index = 0
while batch_index < self.batch_num:
LOGGER.info("batch:{}".format(batch_index))
# set batch_data
# in order to avoid communicating in next iteration
# in next iteration, the sequence of batches is the same
if len(self.batch_index_list) < self.batch_num:
batch_data_index = federation.get(
name=self.transfer_variable.batch_data_index.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.batch_data_index,
self.n_iter_, batch_index),
idx=0)
LOGGER.info("Get batch_index from Guest")
self.batch_index_list.append(batch_index)
else:
batch_data_index = self.batch_index_list[batch_index]
# Get mini-batch train_data
# in order to avoid joining for next iteration
if len(index_data_inst_map) < self.batch_num:
batch_data_inst = batch_data_index.join(
data_instances, lambda g, d: d)
index_data_inst_map[batch_index] = batch_data_inst
else:
batch_data_inst = index_data_inst_map[batch_data_index]
LOGGER.info("batch_data_inst size:{}".format(
batch_data_inst.count()))
#self.transform(data_inst)
# compute forward
host_forward = self.compute_forward(batch_data_inst,
self.embedding_, node2id,
batch_index)
federation.remote(
host_forward,
name=self.transfer_variable.host_forward_dict.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_forward_dict, self.n_iter_,
batch_index),
role=consts.GUEST,
idx=0)
LOGGER.info("Remote host_forward to guest")
# Get optimize host gradient and update model
optim_host_gradient = federation.get(
name=self.transfer_variable.host_optim_gradient.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_optim_gradient,
self.n_iter_, batch_index),
idx=0)
LOGGER.info("Get optim_host_gradient from arbiter")
nodeid_join_gradient = batch_data_inst.join(
optim_host_gradient, lambda instance, gradient:
(node2id[instance.features], gradient))
LOGGER.info("update_model")
self.update_model(nodeid_join_gradient)
# update local model
#training_info = {"iteration": self.n_iter_, "batch_index": batch_index}
#self.update_local_model(fore_gradient, batch_data_inst, self.coef_, **training_info)
batch_index += 1
rubbish_list = [host_forward]
rubbish_clear(rubbish_list)
#######
host_common_embedding = common_node_instances.mapValues(
lambda node: self.embedding_[node2id[node]])
federation.remote(
host_common_embedding,
name=self.transfer_variable.host_common_embedding.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_common_embedding, self.n_iter_,
1),
role=consts.ARBITER,
idx=0)
common_embedding = federation.get(
name=self.transfer_variable.common_embedding.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.common_embedding, self.n_iter_, 1),
idx=0)
self.update_common_nodes(common_embedding, common_nodes, node2id)
#######
is_stopped = federation.get(
name=self.transfer_variable.is_stopped.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.is_stopped,
self.n_iter_,
),
idx=0)
LOGGER.info("Get is_stop flag from arbiter:{}".format(is_stopped))
self.n_iter_ += 1
if is_stopped:
break
LOGGER.info("Reach max iter {}, train mode finish!".format(
self.max_iter))
embedding_table = eggroll.table(name='host',
namespace='node_embedding',
partition=10)
id2node = dict(zip(node2id.values(), node2id.keys()))
for id, embedding in enumerate(self.embedding_):
embedding_table.put(id2node[id], embedding)
embedding_table.save_as(name='host',
namespace='node_embedding',
partition=10)
LOGGER.info("Reach max iter {}, train model finish!".format(
self.max_iter))
def fit(self, data_instances, validate_data=None):
"""
Train linR model of role guest
Parameters
----------
data_instances: Table of Instance, input data
"""
LOGGER.info("Enter hetero_linR_guest fit")
self._abnormal_detection(data_instances)
self.header = self.get_header(data_instances)
self.callback_list.on_train_begin(data_instances, validate_data)
# self.validation_strategy = self.init_validation_strategy(data_instances, validate_data)
self.cipher_operator = self.cipher.gen_paillier_cipher_operator()
use_async = False
if with_weight(data_instances):
if self.model_param.early_stop == "diff":
LOGGER.warning("input data with weight, please use 'weight_diff' for 'early_stop'.")
data_instances = scale_sample_weight(data_instances)
self.gradient_loss_operator.set_use_sample_weight()
LOGGER.debug(f"instance weight scaled; use weighted gradient loss operator")
# LOGGER.debug(f"data_instances after scale: {[v[1].weight for v in list(data_instances.collect())]}")
elif len(self.component_properties.host_party_idlist) == 1:
LOGGER.debug(f"set_use_async")
self.gradient_loss_operator.set_use_async()
use_async = True
self.transfer_variable.use_async.remote(use_async)
LOGGER.info("Generate mini-batch from input data")
self.batch_generator.initialize_batch_generator(data_instances, self.batch_size)
self.gradient_loss_operator.set_total_batch_nums(self.batch_generator.batch_nums)
self.encrypted_calculator = [EncryptModeCalculator(self.cipher_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate) for _
in range(self.batch_generator.batch_nums)]
LOGGER.info("Start initialize model.")
LOGGER.info("fit_intercept:{}".format(self.init_param_obj.fit_intercept))
model_shape = self.get_features_shape(data_instances)
if not self.component_properties.is_warm_start:
w = self.initializer.init_model(model_shape, init_params=self.init_param_obj)
self.model_weights = LinearModelWeights(w, fit_intercept=self.fit_intercept, raise_overflow_error=False)
else:
self.callback_warm_start_init_iter(self.n_iter_)
while self.n_iter_ < self.max_iter:
self.callback_list.on_epoch_begin(self.n_iter_)
LOGGER.info("iter:{}".format(self.n_iter_))
# each iter will get the same batch_data_generator
batch_data_generator = self.batch_generator.generate_batch_data()
self.optimizer.set_iters(self.n_iter_)
batch_index = 0
for batch_data in batch_data_generator:
# Start gradient procedure
optim_guest_gradient = self.gradient_loss_operator.compute_gradient_procedure(
batch_data,
self.encrypted_calculator,
self.model_weights,
self.optimizer,
self.n_iter_,
batch_index
)
loss_norm = self.optimizer.loss_norm(self.model_weights)
self.gradient_loss_operator.compute_loss(batch_data, self.n_iter_, batch_index, loss_norm)
self.model_weights = self.optimizer.update_model(self.model_weights, optim_guest_gradient)
batch_index += 1
self.is_converged = self.converge_procedure.sync_converge_info(suffix=(self.n_iter_,))
LOGGER.info("iter: {}, is_converged: {}".format(self.n_iter_, self.is_converged))
self.callback_list.on_epoch_end(self.n_iter_)
self.n_iter_ += 1
if self.stop_training:
break
if self.is_converged:
break
self.callback_list.on_train_end()
self.set_summary(self.get_model_summary())
def fit(self, data_instances, node2id):
"""
Train ne model pf role host
Parameters
----------
data_instances: Dtable of anchor node, input data
"""
LOGGER.info("Enter hetero_ne host")
self.n_node = len(node2id)
LOGGER.info("Host party has {} nodes".format(self.n_node))
data_instances = data_instances.mapValues(HeteroNEHost.load_data)
LOGGER.info("Transform input data to train instance")
public_key = federation.get(
name=self.transfer_variable.paillier_pubkey.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.paillier_pubkey),
idx=0)
LOGGER.info("Get Publick key from arbiter:{}".format(public_key))
self.encrypt_operator.set_public_key(public_key)
batch_info = federation.get(
name=self.transfer_variable.batch_info.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.batch_info),
idx=0)
LOGGER.info("Get batch_info from guest: {}".format(batch_info))
self.batch_size = batch_info['batch_size']
self.batch_num = batch_info['batch_num']
if self.batch_size < consts.MIN_BATCH_SIZE and self.batch_size != -1:
raise ValueError(
"Batch size get from guest should not less than 10, except -1, batch_size is {}"
.format(self.batch_size))
self.encrypted_calculator = [
EncryptModeCalculator(
self.encrypt_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate)
for _ in range(self.batch_num)
]
LOGGER.info("Start initilize model.")
self.embedding_ = self.initializer.init_model((self.n_node, self.dim),
self.init_param_obj)
self.n_iter_ = 0
index_data_inst_map = {}
while self.n_iter_ < self.max_iter:
LOGGER.info("iter: {}".format(self.n_iter_))
batch_index = 0
while batch_index < self.batch_num:
LOGGER.info("batch:{}".format(batch_index))
# set batch_data
# in order to avoid communicating in next iteration
# in next iteration, the sequence of batches is the same
if len(self.batch_index_list) < self.batch_num:
batch_data_index = federation.get(
name=self.transfer_variable.batch_data_index.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.batch_data_index,
self.n_iter_, batch_index),
idx=0)
LOGGER.info("Get batch_index from Guest")
self.batch_index_list.append(batch_index)
else:
batch_data_index = self.batch_index_list[batch_index]
# Get mini-batch train_data
# in order to avoid joining for next iteration
if len(index_data_inst_map) < self.batch_num:
batch_data_inst = batch_data_index.join(
data_instances, lambda g, d: d)
index_data_inst_map[batch_index] = batch_data_inst
else:
batch_data_inst = index_data_inst_map[batch_data_index]
LOGGER.info("batch_data_inst size:{}".format(
batch_data_inst.count()))
#self.transform(data_inst)
# compute forward
host_forward = self.compute_forward(batch_data_inst,
self.embedding_, node2id,
batch_index)
federation.remote(
host_forward,
name=self.transfer_variable.host_forward_dict.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_forward_dict, self.n_iter_,
batch_index),
role=consts.GUEST,
idx=0)
LOGGER.info("Remote host_forward to guest")
# Get optimize host gradient and update model
optim_host_gradient = federation.get(
name=self.transfer_variable.host_optim_gradient.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_optim_gradient,
self.n_iter_, batch_index),
idx=0)
LOGGER.info("Get optim_host_gradient from arbiter")
nodeid_join_gradient = batch_data_inst.join(
optim_host_gradient, lambda instance, gradient:
(node2id[instance.features], gradient))
LOGGER.info("update_model")
self.update_model(nodeid_join_gradient)
# update local model
#training_info = {"iteration": self.n_iter_, "batch_index": batch_index}
#self.update_local_model(fore_gradient, batch_data_inst, self.coef_, **training_info)
batch_index += 1
rubbish_list = [host_forward]
rubbish_clear(rubbish_list)
is_stopped = federation.get(
name=self.transfer_variable.is_stopped.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.is_stopped,
self.n_iter_,
))
LOGGER.info("Get is_stop flag from arbiter:{}".format(is_stopped))
self.n_iter_ += 1
if is_stopped:
LOGGER.info("Reach max iter {}, train mode finish!".format(
self.max_iter))
embedding_table = eggroll.table(name='host',
namespace='node_embedding',
partition=10)
id2node = dict(zip(node2id.values(), node2id.keys()))
for id, embedding in enumerate(self.embedding_):
embedding_table.put(id2node[id], embedding)
embedding_table.save_as(name='host',
namespace='node_embedding',
partition=10)
LOGGER.info("Reach max iter {}, train model finish!".format(
self.max_iter))
def fit_binary(self, data_instances, validate_data):
self._abnormal_detection(data_instances)
validation_strategy = self.init_validation_strategy(
data_instances, validate_data)
LOGGER.debug(
f"MODEL_STEP Start fin_binary, data count: {data_instances.count()}"
)
self.header = self.get_header(data_instances)
self.cipher_operator = self.cipher.gen_paillier_cipher_operator()
self.batch_generator.initialize_batch_generator(data_instances)
self.encrypted_calculator = [
EncryptModeCalculator(
self.cipher_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate)
for _ in range(self.batch_generator.batch_nums)
]
LOGGER.info("Start initialize model.")
model_shape = self.get_features_shape(data_instances)
# intercept is initialized within FactorizationMachineWeights.
# Skip initializer's intercept part.
fit_intercept = False
if self.init_param_obj.fit_intercept:
fit_intercept = True
self.init_param_obj.fit_intercept = False
w_ = self.initializer.init_model(model_shape,
init_params=self.init_param_obj)
embed_ = np.random.normal(
scale=1 / np.sqrt(self.init_param_obj.embed_size),
size=(model_shape, self.init_param_obj.embed_size))
self.model_weights = \
FactorizationMachineWeights(w_, embed_, fit_intercept=fit_intercept)
while self.n_iter_ < self.max_iter:
LOGGER.info("iter:" + str(self.n_iter_))
batch_data_generator = self.batch_generator.generate_batch_data()
batch_index = 0
self.optimizer.set_iters(self.n_iter_)
for batch_data in batch_data_generator:
LOGGER.debug(
f"MODEL_STEP In Batch {batch_index}, batch data count: {batch_data.count()}"
)
optim_host_gradient = self.gradient_loss_operator.compute_gradient_procedure(
batch_data, self.model_weights, self.encrypted_calculator,
self.optimizer, self.n_iter_, batch_index)
LOGGER.debug(
'optim_host_gradient: {}'.format(optim_host_gradient))
self.gradient_loss_operator.compute_loss(
self.model_weights, self.optimizer, self.n_iter_,
batch_index)
# clip gradient
if self.model_param.clip_gradient and self.model_param.clip_gradient > 0:
optim_host_gradient = np.maximum(
optim_host_gradient, -self.model_param.clip_gradient)
optim_host_gradient = np.minimum(
optim_host_gradient, self.model_param.clip_gradient)
_model_weights = self.optimizer.update_model(
self.model_weights, optim_host_gradient)
self.model_weights.update(_model_weights)
batch_index += 1
self.is_converged = self.converge_procedure.sync_converge_info(
suffix=(self.n_iter_, ))
LOGGER.info("Get is_converged flag from arbiter:{}".format(
self.is_converged))
validation_strategy.validate(self, self.n_iter_)
self.n_iter_ += 1
LOGGER.info("iter: {}, is_converged: {}".format(
self.n_iter_, self.is_converged))
if self.is_converged:
break
LOGGER.debug("Final fm weights: {}".format(self.model_weights.unboxed))
def fit(self, data_instances, validate_data=None):
"""
Train poisson model of role guest
Parameters
----------
data_instances: Table of Instance, input data
"""
LOGGER.info("Enter hetero_poisson_guest fit")
self._abnormal_detection(data_instances)
self.header = copy.deepcopy(self.get_header(data_instances))
self.callback_list.on_train_begin(data_instances, validate_data)
# self.validation_strategy = self.init_validation_strategy(data_instances, validate_data)
if with_weight(data_instances):
LOGGER.warning(
"input data with weight. Poisson regression does not support weighted training."
)
self.exposure_index = self.get_exposure_index(self.header,
self.exposure_colname)
exposure_index = self.exposure_index
if exposure_index > -1:
self.header.pop(exposure_index)
LOGGER.info("Guest provides exposure value.")
exposure = data_instances.mapValues(
lambda v: HeteroPoissonBase.load_exposure(v, exposure_index))
data_instances = data_instances.mapValues(
lambda v: HeteroPoissonBase.load_instance(v, exposure_index))
self.cipher_operator = self.cipher.gen_paillier_cipher_operator()
LOGGER.info("Generate mini-batch from input data")
self.batch_generator.initialize_batch_generator(
data_instances, self.batch_size)
self.encrypted_calculator = [
EncryptModeCalculator(
self.cipher_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate)
for _ in range(self.batch_generator.batch_nums)
]
LOGGER.info("Start initialize model.")
LOGGER.info("fit_intercept:{}".format(
self.init_param_obj.fit_intercept))
model_shape = self.get_features_shape(data_instances)
if not self.component_properties.is_warm_start:
w = self.initializer.init_model(model_shape,
init_params=self.init_param_obj)
self.model_weights = LinearModelWeights(
w,
fit_intercept=self.fit_intercept,
raise_overflow_error=False)
else:
self.callback_warm_start_init_iter(self.n_iter_)
while self.n_iter_ < self.max_iter:
self.callback_list.on_epoch_begin(self.n_iter_)
LOGGER.info("iter:{}".format(self.n_iter_))
# each iter will get the same batch_data_generator
batch_data_generator = self.batch_generator.generate_batch_data()
self.optimizer.set_iters(self.n_iter_)
batch_index = 0
for batch_data in batch_data_generator:
# compute offset of this batch
batch_offset = exposure.join(
batch_data, lambda ei, d: HeteroPoissonBase.safe_log(ei))
# Start gradient procedure
optimized_gradient = self.gradient_loss_operator.compute_gradient_procedure(
batch_data, self.encrypted_calculator, self.model_weights,
self.optimizer, self.n_iter_, batch_index, batch_offset)
# LOGGER.debug("iteration:{} Guest's gradient: {}".format(self.n_iter_, optimized_gradient))
loss_norm = self.optimizer.loss_norm(self.model_weights)
self.gradient_loss_operator.compute_loss(
batch_data, self.model_weights, self.n_iter_, batch_index,
batch_offset, loss_norm)
self.model_weights = self.optimizer.update_model(
self.model_weights, optimized_gradient)
batch_index += 1
self.is_converged = self.converge_procedure.sync_converge_info(
suffix=(self.n_iter_, ))
LOGGER.info("iter: {}, is_converged: {}".format(
self.n_iter_, self.is_converged))
self.callback_list.on_epoch_end(self.n_iter_)
self.n_iter_ += 1
if self.stop_training:
break
if self.is_converged:
break
self.callback_list.on_train_end()
self.set_summary(self.get_model_summary())
def fit_binary(self, data_instances, validate_data=None):
LOGGER.info("Starting to hetero_sshe_logistic_regression")
self.callback_list.on_train_begin(data_instances, validate_data)
model_shape = self.get_features_shape(data_instances)
instances_count = data_instances.count()
if not self.component_properties.is_warm_start:
w = self._init_weights(model_shape)
self.model_weights = LinearModelWeights(
l=w, fit_intercept=self.model_param.init_param.fit_intercept)
last_models = copy.deepcopy(self.model_weights)
else:
last_models = copy.deepcopy(self.model_weights)
w = last_models.unboxed
self.callback_warm_start_init_iter(self.n_iter_)
self.batch_generator.initialize_batch_generator(
data_instances, batch_size=self.batch_size)
with SPDZ(
"sshe_lr",
local_party=self.local_party,
all_parties=self.parties,
q_field=self.q_field,
use_mix_rand=self.model_param.use_mix_rand,
) as spdz:
spdz.set_flowid(self.flowid)
self.secure_matrix_obj.set_flowid(self.flowid)
if self.role == consts.GUEST:
self.labels = data_instances.mapValues(
lambda x: np.array([x.label], dtype=int))
w_self, w_remote = self.share_model(w, suffix="init")
last_w_self, last_w_remote = w_self, w_remote
LOGGER.debug(
f"first_w_self shape: {w_self.shape}, w_remote_shape: {w_remote.shape}"
)
batch_data_generator = self.batch_generator.generate_batch_data()
self.cipher_tool = []
encoded_batch_data = []
for batch_data in batch_data_generator:
if self.fit_intercept:
batch_features = batch_data.mapValues(lambda x: np.hstack(
(x.features, 1.0)))
else:
batch_features = batch_data.mapValues(lambda x: x.features)
self.batch_num.append(batch_data.count())
encoded_batch_data.append(
fixedpoint_table.FixedPointTensor(
self.fixedpoint_encoder.encode(batch_features),
q_field=self.fixedpoint_encoder.n,
endec=self.fixedpoint_encoder))
self.cipher_tool.append(
EncryptModeCalculator(
self.cipher, self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate)
)
while self.n_iter_ < self.max_iter:
self.callback_list.on_epoch_begin(self.n_iter_)
LOGGER.info(f"start to n_iter: {self.n_iter_}")
loss_list = []
self.optimizer.set_iters(self.n_iter_)
if not self.reveal_every_iter:
self.self_optimizer.set_iters(self.n_iter_)
self.remote_optimizer.set_iters(self.n_iter_)
for batch_idx, batch_data in enumerate(encoded_batch_data):
current_suffix = (str(self.n_iter_), str(batch_idx))
if self.reveal_every_iter:
y = self.forward(weights=self.model_weights,
features=batch_data,
suffix=current_suffix,
cipher=self.cipher_tool[batch_idx])
else:
y = self.forward(weights=(w_self, w_remote),
features=batch_data,
suffix=current_suffix,
cipher=self.cipher_tool[batch_idx])
if self.role == consts.GUEST:
error = y - self.labels
self_g, remote_g = self.backward(
error=error,
features=batch_data,
suffix=current_suffix,
cipher=self.cipher_tool[batch_idx])
else:
self_g, remote_g = self.backward(
error=y,
features=batch_data,
suffix=current_suffix,
cipher=self.cipher_tool[batch_idx])
# loss computing;
suffix = ("loss", ) + current_suffix
if self.reveal_every_iter:
batch_loss = self.compute_loss(
weights=self.model_weights,
suffix=suffix,
cipher=self.cipher_tool[batch_idx])
else:
batch_loss = self.compute_loss(
weights=(w_self, w_remote),
suffix=suffix,
cipher=self.cipher_tool[batch_idx])
if batch_loss is not None:
batch_loss = batch_loss * self.batch_num[batch_idx]
loss_list.append(batch_loss)
if self.reveal_every_iter:
# LOGGER.debug(f"before reveal: self_g shape: {self_g.shape}, remote_g_shape: {remote_g}，"
# f"self_g: {self_g}")
new_g = self.reveal_models(self_g,
remote_g,
suffix=current_suffix)
# LOGGER.debug(f"after reveal: new_g shape: {new_g.shape}, new_g: {new_g}"
# f"self.model_param.reveal_strategy: {self.model_param.reveal_strategy}")
if new_g is not None:
self.model_weights = self.optimizer.update_model(
self.model_weights, new_g, has_applied=False)
else:
self.model_weights = LinearModelWeights(
l=np.zeros(self_g.shape),
fit_intercept=self.model_param.init_param.
fit_intercept)
else:
if self.optimizer.penalty == consts.L2_PENALTY:
self_g = self_g + self.self_optimizer.alpha * w_self
remote_g = remote_g + self.remote_optimizer.alpha * w_remote
# LOGGER.debug(f"before optimizer: {self_g}, {remote_g}")
self_g = self.self_optimizer.apply_gradients(self_g)
remote_g = self.remote_optimizer.apply_gradients(
remote_g)
# LOGGER.debug(f"after optimizer: {self_g}, {remote_g}")
w_self -= self_g
w_remote -= remote_g
LOGGER.debug(
f"w_self shape: {w_self.shape}, w_remote_shape: {w_remote.shape}"
)
if self.role == consts.GUEST:
loss = np.sum(loss_list) / instances_count
self.loss_history.append(loss)
if self.need_call_back_loss:
self.callback_loss(self.n_iter_, loss)
else:
loss = None
if self.converge_func_name in ["diff", "abs"]:
self.is_converged = self.check_converge_by_loss(
loss, suffix=(str(self.n_iter_), ))
elif self.converge_func_name == "weight_diff":
if self.reveal_every_iter:
self.is_converged = self.check_converge_by_weights(
last_w=last_models.unboxed,
new_w=self.model_weights.unboxed,
suffix=(str(self.n_iter_), ))
last_models = copy.deepcopy(self.model_weights)
else:
self.is_converged = self.check_converge_by_weights(
last_w=(last_w_self, last_w_remote),
new_w=(w_self, w_remote),
suffix=(str(self.n_iter_), ))
last_w_self, last_w_remote = copy.deepcopy(
w_self), copy.deepcopy(w_remote)
else:
raise ValueError(
f"Cannot recognize early_stop function: {self.converge_func_name}"
)
LOGGER.info("iter: {}, is_converged: {}".format(
self.n_iter_, self.is_converged))
self.callback_list.on_epoch_end(self.n_iter_)
self.n_iter_ += 1
if self.stop_training:
break
if self.is_converged:
break
# Finally reconstruct
if not self.reveal_every_iter:
new_w = self.reveal_models(w_self,
w_remote,
suffix=("final", ))
if new_w is not None:
self.model_weights = LinearModelWeights(
l=new_w,
fit_intercept=self.model_param.init_param.fit_intercept
)
LOGGER.debug(f"loss_history: {self.loss_history}")
self.set_summary(self.get_model_summary())
def fit(self, data_instances, validate_data=None):
"""
Train linR model of role guest
Parameters
----------
data_instances: DTable of Instance, input data
"""
LOGGER.info("Enter hetero_linR_guest fit")
self._abnormal_detection(data_instances)
self.header = self.get_header(data_instances)
self.validation_strategy = self.init_validation_strategy(
data_instances, validate_data)
self.cipher_operator = self.cipher.gen_paillier_cipher_operator()
LOGGER.info("Generate mini-batch from input data")
self.batch_generator.initialize_batch_generator(
data_instances, self.batch_size)
self.gradient_loss_operator.set_total_batch_nums(
self.batch_generator.batch_nums)
self.encrypted_calculator = [
EncryptModeCalculator(
self.cipher_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate)
for _ in range(self.batch_generator.batch_nums)
]
LOGGER.info("Start initialize model.")
LOGGER.info("fit_intercept:{}".format(
self.init_param_obj.fit_intercept))
model_shape = self.get_features_shape(data_instances)
w = self.initializer.init_model(model_shape,
init_params=self.init_param_obj)
self.model_weights = LinearModelWeights(
w, fit_intercept=self.fit_intercept)
while self.n_iter_ < self.max_iter:
LOGGER.info("iter:{}".format(self.n_iter_))
# each iter will get the same batch_data_generator
batch_data_generator = self.batch_generator.generate_batch_data()
self.optimizer.set_iters(self.n_iter_)
batch_index = 0
for batch_data in batch_data_generator:
# transforms features of raw input 'batch_data_inst' into more representative features 'batch_feat_inst'
batch_feat_inst = self.transform(batch_data)
# Start gradient procedure
optim_guest_gradient, _, _ = self.gradient_loss_operator.compute_gradient_procedure(
batch_feat_inst, self.encrypted_calculator,
self.model_weights, self.optimizer, self.n_iter_,
batch_index)
loss_norm = self.optimizer.loss_norm(self.model_weights)
self.gradient_loss_operator.compute_loss(
data_instances, self.n_iter_, batch_index, loss_norm)
self.model_weights = self.optimizer.update_model(
self.model_weights, optim_guest_gradient)
batch_index += 1
# LOGGER.debug(
# "model_weights, iters: {}, update_model: {}".format(self.n_iter_, self.model_weights.unboxed))
self.is_converged = self.converge_procedure.sync_converge_info(
suffix=(self.n_iter_, ))
LOGGER.info("iter: {}, is_converged: {}".format(
self.n_iter_, self.is_converged))
# LOGGER.debug("model weights is {}".format(self.model_weights.coef_))
if self.validation_strategy:
LOGGER.debug('LinR guest running validation')
self.validation_strategy.validate(self, self.n_iter_)
if self.validation_strategy.need_stop():
LOGGER.debug('early stopping triggered')
break
self.n_iter_ += 1
if self.is_converged:
break
if self.validation_strategy and self.validation_strategy.has_saved_best_model(
):
self.load_model(self.validation_strategy.cur_best_model)
def fit(self, data_instances):
"""
Train lr model of role host
Parameters
----------
data_instances: DTable of Instance, input data
"""
LOGGER.info("Enter hetero_lr host")
self._abnormal_detection(data_instances)
self.header = self.get_header(data_instances)
public_key = federation.get(
name=self.transfer_variable.paillier_pubkey.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.paillier_pubkey),
idx=0)
LOGGER.info("Get public_key from arbiter:{}".format(public_key))
self.encrypt_operator.set_public_key(public_key)
batch_info = federation.get(
name=self.transfer_variable.batch_info.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.batch_info),
idx=0)
LOGGER.info("Get batch_info from guest:" + str(batch_info))
self.batch_size = batch_info["batch_size"]
self.batch_num = batch_info["batch_num"]
if self.batch_size < consts.MIN_BATCH_SIZE and self.batch_size != -1:
raise ValueError(
"Batch size get from guest should not less than 10, except -1, batch_size is {}"
.format(self.batch_size))
self.encrypted_calculator = [
EncryptModeCalculator(
self.encrypt_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate)
for _ in range(self.batch_num)
]
LOGGER.info("Start initialize model.")
model_shape = self.get_features_shape(data_instances)
if self.init_param_obj.fit_intercept:
self.init_param_obj.fit_intercept = False
if self.fit_intercept:
self.fit_intercept = False
self.coef_ = self.initializer.init_model(
model_shape, init_params=self.init_param_obj)
self.n_iter_ = 0
index_data_inst_map = {}
while self.n_iter_ < self.max_iter:
LOGGER.info("iter:" + str(self.n_iter_))
batch_index = 0
while batch_index < self.batch_num:
LOGGER.info("batch:{}".format(batch_index))
# set batch_data
if len(self.batch_index_list) < self.batch_num:
batch_data_index = federation.get(
name=self.transfer_variable.batch_data_index.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.batch_data_index,
self.n_iter_, batch_index),
idx=0)
LOGGER.info("Get batch_index from Guest")
self.batch_index_list.append(batch_data_index)
else:
batch_data_index = self.batch_index_list[batch_index]
# Get mini-batch train data
if len(index_data_inst_map) < self.batch_num:
batch_data_inst = batch_data_index.join(
data_instances, lambda g, d: d)
index_data_inst_map[batch_index] = batch_data_inst
else:
batch_data_inst = index_data_inst_map[batch_index]
LOGGER.info("batch_data_inst size:{}".format(
batch_data_inst.count()))
# transforms features of raw input 'batch_data_inst' into more representative features 'batch_feat_inst'
batch_feat_inst = self.transform(batch_data_inst)
# compute forward
host_forward = self.compute_forward(batch_feat_inst,
self.coef_,
self.intercept_,
batch_index)
federation.remote(
host_forward,
name=self.transfer_variable.host_forward_dict.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_forward_dict, self.n_iter_,
batch_index),
role=consts.GUEST,
idx=0)
LOGGER.info("Remote host_forward to guest")
# compute host gradient
fore_gradient = federation.get(
name=self.transfer_variable.fore_gradient.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.fore_gradient, self.n_iter_,
batch_index),
idx=0)
LOGGER.info("Get fore_gradient from guest")
if self.gradient_operator is None:
self.gradient_operator = HeteroLogisticGradient(
self.encrypt_operator)
host_gradient = self.gradient_operator.compute_gradient(
batch_feat_inst, fore_gradient, fit_intercept=False)
# regulation if necessary
if self.updater is not None:
loss_regular = self.updater.loss_norm(self.coef_)
en_loss_regular = self.encrypt_operator.encrypt(
loss_regular)
federation.remote(
en_loss_regular,
name=self.transfer_variable.host_loss_regular.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_loss_regular,
self.n_iter_, batch_index),
role=consts.GUEST,
idx=0)
LOGGER.info("Remote host_loss_regular to guest")
federation.remote(
host_gradient,
name=self.transfer_variable.host_gradient.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_gradient, self.n_iter_,
batch_index),
role=consts.ARBITER,
idx=0)
LOGGER.info("Remote host_gradient to arbiter")
# Get optimize host gradient and update model
optim_host_gradient = federation.get(
name=self.transfer_variable.host_optim_gradient.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.host_optim_gradient,
self.n_iter_, batch_index),
idx=0)
LOGGER.info("Get optim_host_gradient from arbiter")
LOGGER.info("update_model")
self.update_model(optim_host_gradient)
# update local model that transforms features of raw input 'batch_data_inst'
training_info = {
"iteration": self.n_iter_,
"batch_index": batch_index
}
self.update_local_model(fore_gradient, batch_data_inst,
self.coef_, **training_info)
batch_index += 1
# temporary resource recovery and will be removed in the future
rubbish_list = [host_forward, fore_gradient]
data_overview.rubbish_clear(rubbish_list)
is_stopped = federation.get(
name=self.transfer_variable.is_stopped.name,
tag=self.transfer_variable.generate_transferid(
self.transfer_variable.is_stopped, self.n_iter_,
batch_index),
idx=0)
LOGGER.info("Get is_stop flag from arbiter:{}".format(is_stopped))
self.n_iter_ += 1
if is_stopped:
LOGGER.info(
"Get stop signal from arbiter, model is converged, iter:{}"
.format(self.n_iter_))
break
LOGGER.info("Reach max iter {}, train model finish!".format(
self.max_iter))
def fit(self, data_instances, validate_data=None):
"""
Train poisson regression model of role host
Parameters
----------
data_instances: DTable of Instance, input data
"""
LOGGER.info("Enter hetero_poisson host")
self._abnormal_detection(data_instances)
self.validation_strategy = self.init_validation_strategy(
data_instances, validate_data)
self.header = self.get_header(data_instances)
self.cipher_operator = self.cipher.gen_paillier_cipher_operator()
self.batch_generator.initialize_batch_generator(data_instances)
self.encrypted_calculator = [
EncryptModeCalculator(
self.cipher_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate)
for _ in range(self.batch_generator.batch_nums)
]
LOGGER.info("Start initialize model.")
model_shape = self.get_features_shape(data_instances)
if self.init_param_obj.fit_intercept:
self.init_param_obj.fit_intercept = False
w = self.initializer.init_model(model_shape,
init_params=self.init_param_obj)
self.model_weights = LinearModelWeights(
w, fit_intercept=self.fit_intercept)
while self.n_iter_ < self.max_iter:
LOGGER.info("iter:" + str(self.n_iter_))
batch_data_generator = self.batch_generator.generate_batch_data()
self.optimizer.set_iters(self.n_iter_)
batch_index = 0
for batch_data in batch_data_generator:
batch_feat_inst = self.transform(batch_data)
optim_host_gradient, _ = self.gradient_loss_operator.compute_gradient_procedure(
batch_feat_inst, self.encrypted_calculator,
self.model_weights, self.optimizer, self.n_iter_,
batch_index)
self.gradient_loss_operator.compute_loss(
batch_feat_inst, self.model_weights,
self.encrypted_calculator, self.optimizer, self.n_iter_,
batch_index, self.cipher_operator)
self.model_weights = self.optimizer.update_model(
self.model_weights, optim_host_gradient)
batch_index += 1
self.is_converged = self.converge_procedure.sync_converge_info(
suffix=(self.n_iter_, ))
LOGGER.info("Get is_converged flag from arbiter:{}".format(
self.is_converged))
if self.validation_strategy:
LOGGER.debug('Poisson host running validation')
self.validation_strategy.validate(self, self.n_iter_)
if self.validation_strategy.need_stop():
LOGGER.debug('early stopping triggered')
break
self.n_iter_ += 1
LOGGER.info("iter: {}, is_converged: {}".format(
self.n_iter_, self.is_converged))
if self.is_converged:
break
if not self.is_converged:
LOGGER.info("Reach max iter {}, train model finish!".format(
self.max_iter))
if self.validation_strategy and self.validation_strategy.has_saved_best_model(
):
self.load_model(self.validation_strategy.cur_best_model)
self.set_summary(self.get_model_summary())
def fit_binary(self, data_instances, validate_data):
self._abnormal_detection(data_instances)
self.check_abnormal_values(data_instances)
self.check_abnormal_values(validate_data)
# self.validation_strategy = self.init_validation_strategy(data_instances, validate_data)
self.callback_list.on_train_begin(data_instances, validate_data)
LOGGER.debug(f"MODEL_STEP Start fin_binary, data count: {data_instances.count()}")
self.header = self.get_header(data_instances)
self.cipher_operator = self.cipher.gen_paillier_cipher_operator()
if self.transfer_variable.use_async.get(idx=0):
LOGGER.debug(f"set_use_async")
self.gradient_loss_operator.set_use_async()
self.batch_generator.initialize_batch_generator(data_instances)
self.gradient_loss_operator.set_total_batch_nums(self.batch_generator.batch_nums)
self.encrypted_calculator = [EncryptModeCalculator(self.cipher_operator,
self.encrypted_mode_calculator_param.mode,
self.encrypted_mode_calculator_param.re_encrypted_rate) for _
in range(self.batch_generator.batch_nums)]
LOGGER.info("Start initialize model.")
model_shape = self.get_features_shape(data_instances)
if self.init_param_obj.fit_intercept:
self.init_param_obj.fit_intercept = False
if not self.component_properties.is_warm_start:
w = self.initializer.init_model(model_shape, init_params=self.init_param_obj)
self.model_weights = LinearModelWeights(w, fit_intercept=self.init_param_obj.fit_intercept)
else:
self.callback_warm_start_init_iter(self.n_iter_)
while self.n_iter_ < self.max_iter:
self.callback_list.on_epoch_begin(self.n_iter_)
LOGGER.info("iter:" + str(self.n_iter_))
batch_data_generator = self.batch_generator.generate_batch_data()
batch_index = 0
self.optimizer.set_iters(self.n_iter_)
for batch_data in batch_data_generator:
# transforms features of raw input 'batch_data_inst' into more representative features 'batch_feat_inst'
batch_feat_inst = batch_data
# LOGGER.debug(f"MODEL_STEP In Batch {batch_index}, batch data count: {batch_feat_inst.count()}")
optim_host_gradient = self.gradient_loss_operator.compute_gradient_procedure(
batch_feat_inst, self.encrypted_calculator, self.model_weights, self.optimizer, self.n_iter_,
batch_index)
# LOGGER.debug('optim_host_gradient: {}'.format(optim_host_gradient))
self.gradient_loss_operator.compute_loss(self.model_weights, self.optimizer,
self.n_iter_, batch_index, self.cipher_operator)
self.model_weights = self.optimizer.update_model(self.model_weights, optim_host_gradient)
batch_index += 1
self.is_converged = self.converge_procedure.sync_converge_info(suffix=(self.n_iter_,))
LOGGER.info("Get is_converged flag from arbiter:{}".format(self.is_converged))
LOGGER.info("iter: {}, is_converged: {}".format(self.n_iter_, self.is_converged))
LOGGER.debug(f"flowid: {self.flowid}, step_index: {self.n_iter_}")
self.callback_list.on_epoch_end(self.n_iter_)
self.n_iter_ += 1
if self.stop_training:
break
if self.is_converged:
break
self.callback_list.on_train_end()
self.set_summary(self.get_model_summary())