def run_cora_incremental(feat_data, labels, adj_lists, args):
features = nn.Embedding(2708, 1433)
features.weight = nn.Parameter(torch.FloatTensor(feat_data), requires_grad=False)
agg1 = MeanAggregator(features, cuda=True)
enc1 = Encoder(features, 1433, 128, adj_lists, agg1, gcn=True, cuda=False)
agg2 = MeanAggregator(lambda nodes : enc1(nodes).t(), cuda=False)
enc2 = Encoder(lambda nodes : enc1(nodes).t(), enc1.embed_dim, 128, adj_lists, agg2,
base_model=enc1, gcn=True, cuda=False)
enc1.num_samples = 5
enc2.num_samples = 5
graphsage = IncrementSupervisedGraphSage(7, enc2, labels, args)
val_data = Continuum(name="cora", data_type='val', download=True)
val = val_data.nodes()
for i in range(7):
incremental_data = Continuum(name="cora", data_type='train', download=True, task_type=i)
train = incremental_data.nodes()
random.shuffle(train)
print("the size of task: %i"%len(train))
for i in range(0, len(train), args.batch_size):
if i+args.batch_size <= len(train):
batch_nodes = train[i:i+args.batch_size]
else:
batch_nodes = train[i:len(train)]
graphsage.observe(batch_nodes)
val_output = graphsage.forward(val)
print("Validation F1:", f1_score(labels[val], val_output.data.numpy().argmax(axis=1), average="micro"))
def run_pubmed_incremental(feat_data, labels, adj_lists, args):
evaluation_metrics = []
features = nn.Embedding(19717, 500)
features.weight = nn.Parameter(torch.FloatTensor(feat_data),
requires_grad=False)
# features.cuda()
agg1 = MeanAggregator(features, cuda=True)
enc1 = Encoder(features, 500, 128, adj_lists, agg1, gcn=True, cuda=False)
agg2 = MeanAggregator(lambda nodes: enc1(nodes).t(), cuda=False)
enc2 = Encoder(lambda nodes: enc1(nodes).t(),
enc1.embed_dim,
128,
adj_lists,
agg2,
base_model=enc1,
gcn=True,
cuda=False)
enc1.num_samples = 10
enc2.num_samples = 25
graphsage = IncrementSupervisedGraphSage(3, enc2, labels, args)
val_data = Continuum(name="pubmed", data_type='val', download=True)
val = val_data.nodes()
for t in range(val_data.num_class):
incremental_data = Continuum(name="pubmed",
data_type='train',
download=True,
task_type=t)
train = incremental_data.nodes()
random.shuffle(train)
print("the size of task: %i" % len(train))
for i in range(0, len(train), args.batch_size):
if i + args.batch_size <= len(train):
batch_nodes = train[i:i + args.batch_size]
else:
batch_nodes = train[i:len(train)]
graphsage.observe(batch_nodes)
val_output = graphsage.forward(val)
evaluation_metrics.append([
i,
len(train),
f1_score(labels[val],
val_output.data.numpy().argmax(axis=1),
average="micro")
])
return evaluation_metrics
args = parser.parse_args()
print(args)
torch.manual_seed(args.seed)
if __name__ == "__main__":
total_results = []
for memory in [50, 100, 200, 500]:
args.memory_size = memory
results = []
for i in range(args.repeat):
args.seed = i
print(args)
np.random.seed(args.seed)
random.seed(args.seed)
incremental_data = Continuum(name=args.dataset,
data_type='all_train',
download=True,
task_type=0)
num_nodes = len(incremental_data.labels)
adj_lists = incremental_data.neighbors()
feat_data = incremental_data.features.numpy()
labels = incremental_data.labels
if args.dataset == "pubmed":
results.append(
run_pubmed_incremental(feat_data, labels, adj_lists, args))
if args.task_incremental and args.dataset == "cora":
results.append(
run_cora_incremental(feat_data, labels, adj_lists, args))
elif args.dataset == "cora":
results.append(run_cora(feat_data, labels, adj_lists, args))
total_results.append(results)