def FederatedLearning(params, train_data, test_set, train_set_item):
print('Federated Learning with local RBM')
print('\t Initialize global model ......')
global_model_weights, global_model_visible_bias, global_model_hidden_bias = \
init_global_model((params.rbm_visible_unit, params.rbm_hidden_unit))
# load the train data
rec_batch = 64
train_data_loader = torch.utils.data.DataLoader(train_data, batch_size=rec_batch)
precision_each_round, recall_each_round, f_measure_each_round, ndcg_each_round, hit_num_each_round = [], [], [], [], []
print('\t Start Federated Learning communication round ......')
for r in range(params.max_communication_round):
print('\t \t Communication round %d training:' % r)
# 用户随机采样，生成乱序的的用户排序，取前c * N个
perm = np.random.permutation(params.client_num)
sample_user_num = int(params.c * params.client_num)
sample_user = perm[:sample_user_num].tolist()
weight_accountant, visible_bias_accountant, hidden_bias_accountant = [], [], []
error_accountant = []
for u in sample_user:
u_train_data = torch.zeros([params.b, params.rbm_visible_unit])
u_train_data[0] = train_data[u]
# download global model and initialize local RBM
u_rbm = RBM(params.rbm_visible_unit, params.rbm_hidden_unit, params.rbm_k,
global_model_weights, global_model_visible_bias, global_model_hidden_bias,
use_cuda=params.CUDA)
for epoch in range(params.e):
epoch_error = 0.0
if params.CUDA:
u_train_data = u_train_data.cuda()
epoch_error = u_rbm.contrastive_divergence(u_train_data)
error_accountant.append(epoch_error)
weight_accountant.append(u_rbm.weights)
visible_bias_accountant.append(u_rbm.visible_bias)
hidden_bias_accountant.append(u_rbm.hidden_bias)
print('\t \t update the global model')
global_model_weights = 1 / sample_user_num * sum(weight_accountant)
global_model_visible_bias = 1 / sample_user_num * sum(visible_bias_accountant)
global_model_hidden_bias = 1 / sample_user_num * sum(hidden_bias_accountant)
print('\t \t evaluate the global model')
print('********************')
print('the total error is %0.4f' % sum(error_accountant))
precision_mean, recall_mean, f_measure_mean, ndcg_mean, hit_num_mean = evaluate_global_model(global_model_weights, global_model_visible_bias, global_model_hidden_bias,
params.client_num, params.rbm_visible_unit, train_data_loader, test_set, train_set_item,
params.CUDA, rec_batch)
precision_each_round.append(precision_mean)
recall_each_round.append(recall_mean)
f_measure_each_round.append(f_measure_mean)
ndcg_each_round.append(ndcg_mean)
hit_num_each_round.append(hit_num_mean)
print('********************')
return global_model_weights, global_model_visible_bias, global_model_hidden_bias, \
precision_each_round, recall_each_round, f_measure_each_round, ndcg_each_round, hit_num_each_round
########## TRAINING RBM ##########
print('Training RBM...')
rbm = RBM(VISIBLE_UNITS, HIDDEN_UNITS, CD_K, use_cuda=CUDA)
for epoch in range(EPOCHS):
epoch_error = 0.0
for batch, _ in train_loader:
batch = batch.view(len(batch), VISIBLE_UNITS) # flatten input data
if CUDA:
batch = batch.cuda()
batch_error = rbm.contrastive_divergence(batch)
epoch_error += batch_error
print('Epoch Error (epoch=%d): %.4f' % (epoch, epoch_error))
########## EXTRACT FEATURES ##########
print('Extracting features...')
train_features = np.zeros((len(train_dataset), HIDDEN_UNITS))
train_labels = np.zeros(len(train_dataset))
test_features = np.zeros((len(test_dataset), HIDDEN_UNITS))
test_labels = np.zeros(len(test_dataset))
for i, (batch, labels) in enumerate(train_loader):
batch = batch.view(len(batch), VISIBLE_UNITS) # flatten input data
def FederatedLearning(params, train_data, test_set, train_set_item, divide_user, Top_K):
print('Federated Learning with local RBM')
print('\t Initialize global model ......')
global_model_weights, global_model_visible_bias, global_model_hidden_bias = \
init_global_model((params.rbm_visible_unit, params.rbm_hidden_unit))
# load the train data
rec_batch = 64
train_data_loader = torch.utils.data.DataLoader(train_data, batch_size=rec_batch)
precision_each_round, recall_each_round, f_measure_each_round, ndcg_each_round, hit_num_each_round = [], [], [], [], []
area_num = len(divide_user)
area_best = [GlobalBest(Top_K) for i in range(area_num)]
globalbest = GlobalBest(Top_K)
round_train_time = []
print('\t Start Federated Learning communication round ......')
for r in range(params.max_communication_round):
t0 = time.time() # communicatoin round r training start
print('\t \t Communication round %d training:' % r)
# 用户随机采样，生成乱序的的用户排序，取前c * N个
perm = np.random.permutation(params.client_num)
sample_user_num = int(params.c * params.client_num)
sample_user = perm[:sample_user_num].tolist()
weight_accountant, visible_bias_accountant, hidden_bias_accountant = [], [], []
error_accountant = []
# 遍历采样得到的每一个节点（用户），每一个节点的数据训练得到一个RBM模型
for u in sample_user:
u_train_data = torch.zeros([params.b, params.rbm_visible_unit])
u_train_data[0] = train_data[u]
# download global model and initialize local RBM
u_rbm = RBM(params.rbm_visible_unit, params.rbm_hidden_unit, params.rbm_k,
global_model_weights, global_model_visible_bias, global_model_hidden_bias,
use_cuda=params.CUDA)
for epoch in range(params.e):
epoch_error = 0.0
if params.CUDA:
u_train_data = u_train_data.cuda()
epoch_error = u_rbm.contrastive_divergence(u_train_data)
error_accountant.append(epoch_error)
weight_accountant.append(u_rbm.weights)
visible_bias_accountant.append(u_rbm.visible_bias)
hidden_bias_accountant.append(u_rbm.hidden_bias)
# 模型聚合
print('\t \t update the global model')
global_model_weights = 1 / sample_user_num * sum(weight_accountant)
global_model_visible_bias = 1 / sample_user_num * sum(visible_bias_accountant)
global_model_hidden_bias = 1 / sample_user_num * sum(hidden_bias_accountant)
t1 = time.time()
round_train_time.append(t1 - t0)
print('\t \t train time is %0.4f' % (t1 - t0))
print('\t \t evaluate the global model')
print('********************')
print('the total error is %0.4f' % sum(error_accountant))
rec_top_k_list = predict_model(global_model_weights,global_model_visible_bias, global_model_hidden_bias,
params.client_num, params.rbm_visible_unit,
train_data, train_set_item, params.CUDA, rec_batch)
pre, rec, f_mea, ndcg, hit_num, _map = compute_metrice_according_to_rec_list(rec_top_k_list, test_set, params.rbm_visible_unit,
Top_K)
globalbest.update_best_metrics(Top_K, pre, rec, f_mea, ndcg, hit_num, _map, r)
for i in range(area_num):
area_divide_user = divide_user[i]
pre, rec, f_mea, ndcg, hit_num, _map = eval_area_metrics(rec_top_k_list, area_divide_user, params.rbm_visible_unit, test_set,
Top_K)
area_best[i].update_best_metrics(Top_K, pre, rec, f_mea, ndcg, hit_num, _map, r)
print('********************')
print('total train time is %0.4f' % sum(round_train_time))
return area_best, globalbest
