def test_one_community_benchmarks():
pg.load_backend("numpy")
datasets = ["graph9", "bigraph"]
pre = pg.preprocessor(assume_immutability=True, normalization="symmetric")
algorithms = {
"ppr0.85":
pg.PageRank(alpha=0.85, preprocessor=pre, max_iters=10000, tol=1.E-9),
"ppr0.99":
pg.PageRank(alpha=0.99, preprocessor=pre, max_iters=10000, tol=1.E-9),
"hk3":
pg.HeatKernel(t=3, preprocessor=pre, max_iters=10000, tol=1.E-9),
"hk5":
pg.HeatKernel(t=5, preprocessor=pre, max_iters=10000, tol=1.E-9),
"tuned":
pg.ParameterTuner(preprocessor=pre, max_iters=10000, tol=1.E-9),
}
# algorithms = benchmark.create_variations(algorithms, {"": pg.Tautology, "+SO": pg.SeedOversampling})
# loader = pg.load_datasets_one_community(datasets)
# pg.benchmark(algorithms, loader, "time", verbose=True)
loader = pg.load_datasets_one_community(datasets)
pg.benchmark_print(
pg.benchmark_average(
pg.benchmark_ranks(
pg.benchmark(algorithms,
loader,
pg.AUC,
fraction_of_training=.8))))
def test_gnn_errors():
graph, features, labels = pg.load_feature_dataset('synthfeats')
training, test = pg.split(list(range(len(graph))), 0.8)
training, validation = pg.split(training, 1 - 0.2 / 0.8)
from tensorflow.keras.layers import Dropout, Dense
from tensorflow.keras.regularizers import L2
class APPNP(tf.keras.Sequential):
def __init__(self, num_inputs, num_outputs, hidden=64):
super().__init__([
Dropout(0.5, input_shape=(num_inputs,)),
Dense(hidden, activation="relu", kernel_regularizer=L2(1.E-5)),
Dropout(0.5),
Dense(num_outputs, activation="relu")])
self.ranker = pg.PageRank(0.9, renormalize=True, assume_immutability=True,
use_quotient=False, error_type="iters", max_iters=10) # 10 iterations
def call(self, features, graph, training=False):
predict = super().call(features, training=training)
propagate = self.ranker.propagate(graph, predict, graph_dropout=0.5 if training else 0)
return tf.nn.softmax(propagate, axis=1)
model = APPNP(features.shape[1], labels.shape[1])
with pytest.raises(Exception):
pg.gnn_train(model, graph, features, labels, training, validation, test=test, epochs=2)
pg.load_backend('tensorflow')
pg.gnn_train(model, features, graph, labels, training, validation, test=test, epochs=300, patience=2)
predictions = model(features, graph)
pg.load_backend('numpy')
with pytest.raises(Exception):
pg.gnn_accuracy(labels, predictions, test)
def test_appnp_torch():
graph, features, labels = pg.load_feature_dataset('synthfeats')
training, test = pg.split(list(range(len(graph))), 0.8)
training, validation = pg.split(training, 1 - 0.2 / 0.8)
class AutotuneAPPNP(torch.nn.Module):
def __init__(self, num_inputs, num_outputs, hidden=64):
super().__init__()
self.layer1 = torch.nn.Linear(num_inputs, hidden)
self.layer2 = torch.nn.Linear(hidden, num_outputs)
self.activation = torch.nn.ReLU()
self.dropout = torch.nn.Dropout(0.5)
self.num_outputs = num_outputs
self.ranker = pg.PageRank(0.9,
renormalize=True,
assume_immutability=True,
error_type="iters",
max_iters=10)
def forward(self, inputs, training=False):
graph, features = inputs
predict = self.dropout(torch.FloatTensor(features))
predict = self.dropout(self.activation(self.layer1(predict)))
predict = self.activation(self.layer2(predict))
predict = self.ranker.propagate(
graph, predict, graph_dropout=0.5 if training else 0)
ret = torch.nn.functional.softmax(predict, dim=1)
self.loss = 0
for param in self.layer1.parameters():
self.loss = self.loss + 1E-5 * torch.norm(param)
return ret
def init_weights(m):
if isinstance(m, torch.nn.Linear):
torch.nn.init.xavier_uniform_(m.weight)
m.bias.data.fill_(0.01)
pg.load_backend('pytorch')
model = AutotuneAPPNP(features.shape[1], labels.shape[1])
model.apply(init_weights)
pg.gnn_train(model,
graph,
features,
labels,
training,
validation,
epochs=50,
patience=2)
# TODO: higher numbers fail only on github actions - for local tests it is fine
assert float(pg.gnn_accuracy(labels, model([graph, features]),
test)) >= 0.2
pg.load_backend('numpy')
def test_backend_load():
pg.load_backend("tensorflow")
assert pg.backend_name() == "tensorflow"
pg.load_backend("matvec")
assert pg.backend_name() == "matvec"
pg.load_backend("numpy")
assert pg.backend_name() == "numpy"
with pytest.raises(Exception):
pg.load_backend("unknown")
assert pg.backend_name() == "numpy"
def test_optimization_dict():
pg.load_backend("numpy")
from timeit import default_timer as time
graph = next(pg.load_datasets_graph(["bigraph"]))
personalization = {str(i): 1 for i in range(200)}
preprocessor = pg.preprocessor(assume_immutability=True)
preprocessor(graph)
tic = time()
for _ in range(10):
pg.ParameterTuner(preprocessor=preprocessor, tol=1.E-9).rank(graph, personalization)
unoptimized = time()-tic
optimization = dict()
tic = time()
for _ in range(10):
pg.ParameterTuner(optimization_dict=optimization, preprocessor=preprocessor, tol=1.E-9).rank(graph, personalization)
optimized = time() - tic
assert len(optimization) == 20
assert unoptimized > optimized
def test_appnp_tf():
graph, features, labels = pg.load_feature_dataset('synthfeats')
training, test = pg.split(list(range(len(graph))), 0.8)
training, validation = pg.split(training, 1 - 0.2 / 0.8)
class APPNP(tf.keras.Sequential):
def __init__(self, num_inputs, num_outputs, hidden=64):
super().__init__([
tf.keras.layers.Dropout(0.5, input_shape=(num_inputs, )),
tf.keras.layers.Dense(
hidden,
activation=tf.nn.relu,
kernel_regularizer=tf.keras.regularizers.L2(1.E-5)),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.Dense(num_outputs, activation=tf.nn.relu),
])
self.ranker = pg.PageRank(0.9,
renormalize=True,
assume_immutability=True,
error_type="iters",
max_iters=10)
self.input_spec = None # prevents some versions of tensorflow from checking call inputs
def call(self, inputs, training=False):
graph, features = inputs
predict = super().call(features, training=training)
predict = self.ranker.propagate(
graph, predict, graph_dropout=0.5 if training else 0)
return tf.nn.softmax(predict, axis=1)
pg.load_backend('tensorflow')
model = APPNP(features.shape[1], labels.shape[1])
pg.gnn_train(model,
graph,
features,
labels,
training,
validation,
test=test,
epochs=50)
assert float(pg.gnn_accuracy(labels, model([graph, features]),
test)) >= 0.5
pg.load_backend('numpy')
self.num_outputs = num_outputs
self.propagate_on_training = propagate_on_training
def call(self, inputs, training=False):
graph, features = inputs
predict = super().call(features, training=training)
if not training or self.propagate_on_training:
predict = self.ranker.propagate(
graph,
predict,
graph_dropout=self.graph_dropout if training else 0)
return tf.nn.softmax(predict, axis=1)
pg.load_backend('numpy')
graph, features, labels = pg.load_feature_dataset('cora')
for seed in range(10):
training, test = pg.split(list(range(len(graph))), 0.8, seed=seed)
training, validation = pg.split(training, 1 - 0.2 / 0.8, seed=seed)
architectures = {
"APPNP": APPNP(features.shape[1], labels.shape[1], alpha=0.9),
#"LAPPNP": APPNP(features.shape[1], labels.shape[1], alpha=tf.Variable([0.85])),
"APFNP": APPNP(features.shape[1], labels.shape[1], alpha="estimated")
}
pg.load_backend('tensorflow')
accs = dict()
for architecture, model in architectures.items():
pg.gnn_train(model,
graph,
def supported_backends():
for backend in [
"matvec", "pytorch", "tensorflow", "torch_sparse", "numpy"
]:
pg.load_backend(backend)
yield backend
def supported_backends():
for backend in ["pytorch", "tensorflow", "numpy"]:
pg.load_backend(backend)
yield backend
min_vals=[0.5, 5],
measure=pg.Mabs,
deviation_tol=0.1,
tuning_backend="numpy")
def call(self, inputs, training=False):
graph, features = inputs
predict = super().call(features, training=training)
propagate = self.ranker.propagate(graph,
predict,
graph_dropout=0.5 if training else 0)
return tf.nn.softmax(propagate, axis=1)
graph, features, labels = pg.load_feature_dataset('citeseer')
acc = 0
for _ in range(10):
training, test = pg.split(list(range(len(graph))), 0.8)
training, validation = pg.split(training, 1 - 0.2 / 0.8)
pg.load_backend('tensorflow') # explicitly load the appropriate backend
model = APPNP(features.shape[1], labels.shape[1])
pg.gnn_train(model,
graph,
features,
labels,
training,
validation,
optimizer=tf.optimizers.Adam(learning_rate=0.01))
acc += pg.gnn_accuracy(labels, model([graph, features]), test) / 10
print("Accuracy", pg.gnn_accuracy(labels, model([graph, features]), test))
print(acc)
import pygrank as pg
pg.load_backend("matvec")
#datasets = ["amazon", "citeseer", "maven"]
datasets = ["amazon"]
community_size = 500
pre = pg.preprocessor(assume_immutability=True, normalization="symmetric")
convergence = {"tol": 1.E-9, "max_iters": 10000}
#convergence = {"error_type": "iters", "max_iters": 20}
tuned = [1]+[10000, 0.7573524630180889, 0.0, 1.0, 0.004950495049504955, 0.4975492598764827, 0.2573767277717871, 0.0, 0.2549259876482698, 0.009851975296539583, 0.5, 0.5, 0.5, 0.2549259876482698, 0.5, 0.5, 0.5, 0.009851975296539583, 0.009851975296539583, 0.25002450740123516, 0.2524752475247525, 0.0, 0.5, 0.0, 0.009851975296539583, 0.0, 0.004950495049504955, 0.0, 0.5, 0.004950495049504955, 0.7475247524752475, 0.004950495049504955, 0.009851975296539583, 0.0, 0.995049504950495, 0.0, 0.5, 0.0, 0.004950495049504955, 0.0]
algorithms = {
"ppr0.5": pg.PageRank(alpha=0.5, preprocessor=pre, **convergence),
"ppr0.85": pg.PageRank(alpha=0.85, preprocessor=pre, **convergence),
"ppr0.9": pg.PageRank(alpha=0.9, preprocessor=pre, **convergence),
"ppr0.99": pg.PageRank(alpha=0.99, preprocessor=pre, **convergence),
"hk2": pg.HeatKernel(t=2, preprocessor=pre, **convergence),
"hk3": pg.HeatKernel(t=3, preprocessor=pre, **convergence),
"hk5": pg.HeatKernel(t=5, preprocessor=pre, **convergence),
"hk7": pg.HeatKernel(t=7, preprocessor=pre, **convergence),
#"exp": pg.GenericGraphFilter(tuned, preprocessor=pre, error_type="iters", max_iters=41)
}
postprocessor = pg.Tautology
algorithms = pg.benchmarks.create_variations(algorithms, postprocessor)
measure = pg.Time
optimization = pg.SelfClearDict()