def run(args, seed):
setup_seed(seed)
adj, features, labels, idx_train, idx_val, idx_test = load_data(
args['dataset'])
node_num = features.size()[0]
class_num = labels.numpy().max() + 1
adj = adj.cuda()
features = features.cuda()
labels = labels.cuda()
loss_func = nn.CrossEntropyLoss()
early_stopping = 10
adj_raw = load_adj_raw(args['dataset']).tocoo()
ss_labels = partition(adj_raw, args['partitioning_num']).cuda()
net_gcn = net.net_gcn_multitask(embedding_dim=args['embedding_dim'],
ss_dim=args['partitioning_num'])
net_gcn = net_gcn.cuda()
optimizer = torch.optim.Adam(net_gcn.parameters(),
lr=args['lr'],
weight_decay=args['weight_decay'])
loss_val = []
for epoch in range(1000):
optimizer.zero_grad()
output, output_ss = net_gcn(features, adj)
loss_target = loss_func(output[idx_train], labels[idx_train])
loss_ss = loss_func(output_ss, ss_labels)
loss = loss_target * args['loss_weight'] + loss_ss * (
1 - args['loss_weight'])
# print('epoch', epoch, 'loss', loss_target.data)
loss.backward()
optimizer.step()
# validation
with torch.no_grad():
output, _ = net_gcn(features, adj, val_test=True)
loss_val.append(
loss_func(output[idx_val], labels[idx_val]).cpu().numpy())
# print('val acc', f1_score(labels[idx_val].cpu().numpy(), output[idx_val].cpu().numpy().argmax(axis=1), average='micro'))
# early stopping
if epoch > early_stopping and loss_val[-1] > np.mean(
loss_val[-(early_stopping + 1):-1]):
break
# test
with torch.no_grad():
output, _ = net_gcn(features, adj, val_test=True)
acc_val = f1_score(labels[idx_val].cpu().numpy(),
output[idx_val].cpu().numpy().argmax(axis=1),
average='micro')
acc_test = f1_score(labels[idx_test].cpu().numpy(),
output[idx_test].cpu().numpy().argmax(axis=1),
average='micro')
return acc_val, acc_test
def run(args, seed):
setup_seed(seed)
adj, features, labels, idx_train, idx_val, idx_test = load_data(args['dataset'])
adj = load_adj_raw(args['dataset'])
node_num = features.size()[0]
class_num = labels.numpy().max() + 1
g = dgl.DGLGraph()
g.add_nodes(node_num)
adj = adj.tocoo()
g.add_edges(adj.row, adj.col)
features = features.cuda()
'''
adj = adj.cuda()
features = features.cuda()
'''
labels = labels.cuda()
loss_func = nn.CrossEntropyLoss()
early_stopping = 10
if args['net'] == 'gin':
net_gcn = GINNet(args['embedding_dim'])
else:
net_gcn = GATNet(args['embedding_dim'])
g.add_edges(list(range(node_num)), list(range(node_num)))
net_gcn = net_gcn.cuda()
optimizer = torch.optim.Adam(net_gcn.parameters(), lr=args['lr'], weight_decay=args['weight_decay'])
loss_val = []
for epoch in range(1000):
optimizer.zero_grad()
output = net_gcn(g, features, 0, 0)
loss = loss_func(output[idx_train], labels[idx_train])
# print('epoch', epoch, 'loss', loss.data)
loss.backward()
optimizer.step()
# validation
with torch.no_grad():
net_gcn.eval()
output = net_gcn(g, features, 0, 0)
loss_val.append(loss_func(output[idx_val], labels[idx_val]).cpu().numpy())
# print('val acc', f1_score(labels[idx_val].cpu().numpy(), output[idx_val].cpu().numpy().argmax(axis=1), average='micro'))
# early stopping
if epoch > early_stopping and loss_val[-1] > np.mean(loss_val[-(early_stopping+1):-1]):
break
# test
with torch.no_grad():
net_gcn.eval()
output = net_gcn(g, features, 0, 0)
acc_val = f1_score(labels[idx_val].cpu().numpy(), output[idx_val].cpu().numpy().argmax(axis=1), average='micro')
acc_test = f1_score(labels[idx_test].cpu().numpy(), output[idx_test].cpu().numpy().argmax(axis=1), average='micro')
return acc_val, acc_test
def run(args, seed):
setup_seed(seed)
adj, features, labels, idx_train, idx_val, idx_test = load_data(args['dataset'])
node_num = features.size()[0]
class_num = labels.numpy().max() + 1
adj = adj.cuda()
features = features.cuda()
labels = labels.cuda()
loss_func = nn.CrossEntropyLoss()
loss_func_ss = nn.L1Loss()
early_stopping = 10
adj_raw = load_adj_raw(args['dataset']).tocsr()
idx_mask = list(range(node_num))
adj_mask = adj_raw
adj_mask[idx_mask, idx_mask] = 0
adj_mask = sparse_mx_to_torch_sparse_tensor(normalize_adj(adj_mask)).cuda()
reduced_dim = args['reduced_dimension']
ss_labels, _, _ = features.svd()
ss_labels = ss_labels[:, :reduced_dim].cuda()
net_gcn = net.net_gcn_multitask(embedding_dim=args['embedding_dim'], ss_dim=args['reduced_dimension'])
net_gcn = net_gcn.cuda()
optimizer = torch.optim.Adam(net_gcn.parameters(), lr=args['lr'], weight_decay=args['weight_decay'])
best_val = 0
best_val_test = 0
for epoch in range(500):
optimizer.zero_grad()
output, _ = net_gcn(features, adj)
_, output_ss = net_gcn(features, adj_mask)
loss_target = loss_func(output[idx_train], labels[idx_train])
loss_ss = loss_func_ss(output_ss, ss_labels) * 1e2
loss = loss_target + loss_ss * args['loss_weight']
# print('epoch', epoch, 'loss', loss_target.data)
loss.backward()
optimizer.step()
# validation
with torch.no_grad():
output, _ = net_gcn(features, adj, val_test=True)
# loss_val.append(loss_func(output[idx_val], labels[idx_val]).cpu().numpy())
# print('val acc', f1_score(labels[idx_val].cpu().numpy(), output[idx_val].cpu().numpy().argmax(axis=1), average='micro'))
acc_val = f1_score(labels[idx_val].cpu().numpy(), output[idx_val].cpu().numpy().argmax(axis=1), average='micro')
acc_test = f1_score(labels[idx_test].cpu().numpy(), output[idx_test].cpu().numpy().argmax(axis=1), average='micro')
if acc_val > best_val:
best_val = acc_val
best_val_test = acc_test
return best_val, best_val_test
def run_fix_mask(args, imp_num, adj_percent, wei_percent):
pruning.setup_seed(args['seed'])
adj, features, labels, idx_train, idx_val, idx_test = load_data(
args['dataset'])
adj = load_adj_raw(args['dataset'])
node_num = features.size()[0]
class_num = labels.numpy().max() + 1
g = dgl.DGLGraph()
g.add_nodes(node_num)
adj = adj.tocoo()
g.add_edges(adj.row, adj.col)
features = features.cuda()
labels = labels.cuda()
loss_func = nn.CrossEntropyLoss()
if args['net'] == 'gin':
net_gcn = GINNet(args['embedding_dim'], g)
pruning_gin.add_mask(net_gcn)
pruning_gin.random_pruning(net_gcn, adj_percent, wei_percent)
adj_spar, wei_spar = pruning_gin.print_sparsity(net_gcn)
elif args['net'] == 'gat':
net_gcn = GATNet(args['embedding_dim'], g)
g.add_edges(list(range(node_num)), list(range(node_num)))
pruning_gat.add_mask(net_gcn)
pruning_gat.random_pruning(net_gcn, adj_percent, wei_percent)
adj_spar, wei_spar = pruning_gat.print_sparsity(net_gcn)
else:
assert False
net_gcn = net_gcn.cuda()
for name, param in net_gcn.named_parameters():
if 'mask' in name:
param.requires_grad = False
optimizer = torch.optim.Adam(net_gcn.parameters(),
lr=args['lr'],
weight_decay=args['weight_decay'])
best_val_acc = {'val_acc': 0, 'epoch': 0, 'test_acc': 0}
for epoch in range(args['fix_epoch']):
optimizer.zero_grad()
output = net_gcn(g, features, 0, 0)
loss = loss_func(output[idx_train], labels[idx_train])
loss.backward()
optimizer.step()
with torch.no_grad():
net_gcn.eval()
output = net_gcn(g, features, 0, 0)
acc_val = f1_score(labels[idx_val].cpu().numpy(),
output[idx_val].cpu().numpy().argmax(axis=1),
average='micro')
acc_test = f1_score(labels[idx_test].cpu().numpy(),
output[idx_test].cpu().numpy().argmax(axis=1),
average='micro')
if acc_val > best_val_acc['val_acc']:
best_val_acc['val_acc'] = acc_val
best_val_acc['test_acc'] = acc_test
best_val_acc['epoch'] = epoch
print(
"RP[{}] (Fix Mask) Epoch:[{}/{}] LOSS:[{:.4f}] Val:[{:.2f}] Test:[{:.2f}] | Final Val:[{:.2f}] Test:[{:.2f}] at Epoch:[{}]"
.format(imp_num, epoch, args['fix_epoch'], loss, acc_val * 100,
acc_test * 100, best_val_acc['val_acc'] * 100,
best_val_acc['test_acc'] * 100, best_val_acc['epoch']))
print(
"syd final: [{},{}] RP[{}] (Fix Mask) Final Val:[{:.2f}] Test:[{:.2f}] at Epoch:[{}] | Adj:[{:.2f}%] Wei:[{:.2f}%]"
.format(args['dataset'], args['net'], imp_num,
best_val_acc['val_acc'] * 100, best_val_acc['test_acc'] * 100,
best_val_acc['epoch'], adj_spar, wei_spar))
def run_get_mask(args, imp_num, rewind_weight_mask=None):
pruning.setup_seed(args['seed'])
adj, features, labels, idx_train, idx_val, idx_test = load_data(
args['dataset'])
adj = load_adj_raw(args['dataset'])
node_num = features.size()[0]
class_num = labels.numpy().max() + 1
g = dgl.DGLGraph()
g.add_nodes(node_num)
adj = adj.tocoo()
g.add_edges(adj.row, adj.col)
features = features.cuda()
labels = labels.cuda()
loss_func = nn.CrossEntropyLoss()
if args['net'] == 'gin':
net_gcn = GINNet(args['embedding_dim'], g)
pruning_gin.add_mask(net_gcn)
elif args['net'] == 'gat':
net_gcn = GATNet(args['embedding_dim'], g)
g.add_edges(list(range(node_num)), list(range(node_num)))
pruning_gat.add_mask(net_gcn)
else:
assert False
net_gcn = net_gcn.cuda()
if rewind_weight_mask:
net_gcn.load_state_dict(rewind_weight_mask)
if args['net'] == 'gin':
pruning_gin.add_trainable_mask_noise(net_gcn, c=1e-5)
adj_spar, wei_spar = pruning_gin.print_sparsity(net_gcn)
else:
pruning_gat.add_trainable_mask_noise(net_gcn, c=1e-5)
adj_spar, wei_spar = pruning_gat.print_sparsity(net_gcn)
optimizer = torch.optim.Adam(net_gcn.parameters(),
lr=args['lr'],
weight_decay=args['weight_decay'])
best_val_acc = {'val_acc': 0, 'epoch': 0, 'test_acc': 0}
rewind_weight = copy.deepcopy(net_gcn.state_dict())
for epoch in range(args['mask_epoch']):
optimizer.zero_grad()
output = net_gcn(g, features, 0, 0)
loss = loss_func(output[idx_train], labels[idx_train])
loss.backward()
if args['net'] == 'gin':
pruning_gin.subgradient_update_mask(net_gcn, args) # l1 norm
else:
pruning_gat.subgradient_update_mask(net_gcn, args) # l1 norm
optimizer.step()
with torch.no_grad():
net_gcn.eval()
output = net_gcn(g, features, 0, 0)
acc_val = f1_score(labels[idx_val].cpu().numpy(),
output[idx_val].cpu().numpy().argmax(axis=1),
average='micro')
acc_test = f1_score(labels[idx_test].cpu().numpy(),
output[idx_test].cpu().numpy().argmax(axis=1),
average='micro')
if acc_val > best_val_acc['val_acc']:
best_val_acc['val_acc'] = acc_val
best_val_acc['test_acc'] = acc_test
best_val_acc['epoch'] = epoch
if args['net'] == 'gin':
rewind_weight, adj_spar, wei_spar = pruning_gin.get_final_mask_epoch(
net_gcn, rewind_weight, args)
else:
rewind_weight, adj_spar, wei_spar = pruning_gat.get_final_mask_epoch(
net_gcn, rewind_weight, args)
print(
"IMP[{}] (Get Mask) Epoch:[{}/{}] LOSS:[{:.4f}] Val:[{:.2f}] Test:[{:.2f}] | Final Val:[{:.2f}] Test:[{:.2f}] at Epoch:[{}] | Adj:[{:.2f}%] Wei:[{:.2f}%]"
.format(imp_num, epoch, args['mask_epoch'], loss, acc_val * 100,
acc_test * 100, best_val_acc['val_acc'] * 100,
best_val_acc['test_acc'] * 100, best_val_acc['epoch'],
adj_spar, wei_spar))
return rewind_weight
def run(args, seed):
setup_seed(seed)
adj, features, labels, idx_train, idx_val, idx_test = load_data(args['dataset'])
adj = load_adj_raw(args['dataset'])
node_num = features.size()[0]
class_num = labels.numpy().max() + 1
g = dgl.DGLGraph().to('cuda:%s' % args['cuda'] )
print(g.device)
g.add_nodes(node_num)
adj = adj.tocoo()
g.add_edges(adj.row, adj.col)
# adj = adj.cuda()
features = features.cuda()
labels = labels.cuda()
loss_func = nn.CrossEntropyLoss()
loss_func_ss = nn.L1Loss()
early_stopping = 10
if args['net'] == 'gin':
net_gcn = GINNet_ss(args['embedding_dim'], args['reduced_dimension'])
else:
net_gcn = GATNet_ss(args['embedding_dim'], args['reduced_dimension'])
g.add_edges(list(range(node_num)), list(range(node_num)))
adj_raw = load_adj_raw(args['dataset']).tocsr()
idx_mask = list(range(node_num))
adj_mask = adj_raw
adj_mask[idx_mask, idx_mask] = 0
adj_mask = sparse_mx_to_torch_sparse_tensor(normalize_adj(adj_mask)).cuda()
reduced_dim = args['reduced_dimension']
ss_labels, _, _ = features.svd()
ss_labels = ss_labels[:, :reduced_dim].cuda()
net_gcn = net_gcn.cuda()
optimizer = torch.optim.Adam(net_gcn.parameters(), lr=args['lr'], weight_decay=args['weight_decay'])
best_val = 0
best_val_test = 0
for epoch in range(400):
optimizer.zero_grad()
output, output_ss = net_gcn(g, features, 0, 0)
loss_target = loss_func(output[idx_train], labels[idx_train])
loss_ss = loss_func_ss(output_ss, ss_labels) * 1e2
loss = loss_target + loss_ss * args['loss_weight']
# print('epoch', epoch, 'loss', loss_target.data)
loss.backward()
optimizer.step()
# validation
with torch.no_grad():
net_gcn.eval()
output, _ = net_gcn(g, features, 0, 0)
# loss_val.append(loss_func(output[idx_val], labels[idx_val]).cpu().numpy())
# print('val acc', f1_score(labels[idx_val].cpu().numpy(), output[idx_val].cpu().numpy().argmax(axis=1), average='micro'))
wandb.log({
'val_acc': f1_score(labels[idx_val].cpu().numpy(), output[idx_val].cpu().numpy().argmax(axis=1), average='micro')
})
acc_val = f1_score(labels[idx_val].cpu().numpy(), output[idx_val].cpu().numpy().argmax(axis=1), average='micro')
acc_test = f1_score(labels[idx_test].cpu().numpy(), output[idx_test].cpu().numpy().argmax(axis=1), average='micro')
if acc_val > best_val:
best_val = acc_val
best_val_test = acc_test
return best_val, best_val_test
def run(args):
pruning.setup_seed(args['seed'])
adj, features, labels, idx_train, idx_val, idx_test = load_data(
args['dataset'])
adj = load_adj_raw(args['dataset'])
node_num = features.size()[0]
class_num = labels.numpy().max() + 1
g = dgl.DGLGraph()
g.add_nodes(node_num)
adj = adj.tocoo()
g.add_edges(adj.row, adj.col)
features = features.cuda()
labels = labels.cuda()
loss_func = nn.CrossEntropyLoss()
if args['net'] == 'gin':
net_gcn = GINNet(args['embedding_dim'])
else:
net_gcn = GATNet(args['embedding_dim'])
g.add_edges(list(range(node_num)), list(range(node_num)))
net_gcn = net_gcn.cuda()
optimizer = torch.optim.Adam(net_gcn.parameters(),
lr=args['lr'],
weight_decay=args['weight_decay'])
best_val_acc = {'val_acc': 0, 'epoch': 0, 'test_acc': 0}
for epoch in range(args['total_epoch']):
optimizer.zero_grad()
output = net_gcn(g, features, 0, 0)
loss = loss_func(output[idx_train], labels[idx_train])
loss.backward()
optimizer.step()
with torch.no_grad():
net_gcn.eval()
output = net_gcn(g, features, 0, 0)
acc_val = f1_score(labels[idx_val].cpu().numpy(),
output[idx_val].cpu().numpy().argmax(axis=1),
average='micro')
acc_test = f1_score(labels[idx_test].cpu().numpy(),
output[idx_test].cpu().numpy().argmax(axis=1),
average='micro')
if acc_val > best_val_acc['val_acc']:
best_val_acc['val_acc'] = acc_val
best_val_acc['test_acc'] = acc_test
best_val_acc['epoch'] = epoch
print(
"(Baseline) Epoch:[{}] LOSS:[{:.2f}] Val:[{:.2f}] Test:[{:.2f}] | Final Val:[{:.2f}] Test:[{:.2f}] at Epoch:[{}]"
.format(epoch, loss, acc_val * 100, acc_test * 100,
best_val_acc['val_acc'] * 100,
best_val_acc['test_acc'] * 100, best_val_acc['epoch']))
print(
"syd final: [{},{}] (Baseline) Final Val:[{:.2f}] Test:[{:.2f}] at Epoch:[{}]"
.format(args['dataset'], args['net'], best_val_acc['val_acc'] * 100,
best_val_acc['test_acc'] * 100, best_val_acc['epoch']))