def build_default_args_for_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.001,
"weight_decay": 0,
"max_epoch": 1000,
"max_epochs": 1000,
"patience": 20,
"cpu": cpu,
"device_id": [0],
"seed": [0],
"num_shuffle": 5,
"drop_edge_rates": [0.1, 0.2],
"drop_feature_rates": [0.2, 0.3],
"hidden_size": 128,
"num_layers": 2,
"proj_hidden_size": 128,
"tau": 0.4,
"activation": "relu",
"sampler": "none",
"task": "unsupervised_node_classification",
"model": "grace",
"dataset": dataset,
"save_dir": "./saved",
"enhance": None,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_graph_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.001,
"weight_decay": 5e-4,
"max_epoch": 500,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [0],
"hidden_size": 64,
"degree_feature": False,
"gamma": 0.5,
"kfold": False,
"uniform_feature": False,
"train_ratio": 0.7,
"test_ratio": 0.1,
"num_layers": 3,
"dropout": 0.5,
"batch_size": 128,
"kernel_size": 5,
"k": 30,
"out_channels": 32,
"task": "graph_classification",
"model": "sortpool",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.01,
"weight_decay": 5e-4,
"max_epoch": 1000,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [100],
"input_dropout": 0.5,
"hidden_dropout": 0.5,
"hidden_size": 32,
"dropnode_rate": 0.5,
"order": 5,
"tem": 0.5,
"lam": 0.5,
"sample": 10,
"alpha": 0.2,
"bn": False,
"task": "node_classification",
"model": "grand",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.01,
"weight_decay": 0.0005,
"max_epoch": 1000,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [1],
"n_dropout": 0.90,
"adj_dropout": 0.05,
"hidden_size": 128,
"aug_adj": False,
"improved": False,
"n_pool": 4,
"pool_rate": [0.7, 0.5, 0.5, 0.4],
"activation": "relu",
"task": "node_classification",
"model": "unet",
"dataset": dataset,
"missing_rate": -1,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.005,
"weight_decay": 5e-4,
"max_epoch": 1300,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [
0,
],
"dropout": 0.5,
"hidden_size": 8,
"attention_type": "node",
"normalization": "row_uniform",
"num_heads": 8,
"nhtop": 1,
"node_dropout": 0.5,
"subheads": 1,
"activation": "leaky_relu",
"alpha": 0.2,
"task": "node_classification",
"model": "gcn",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_unsupervisde_graph_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.0001,
"weight_decay": 5e-4,
"max_epoch": 500,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [0],
"num_shuffle": 10,
"epoch": 15,
"train_num": 5000,
"unsup": True,
"hidden_size": 512,
"degree_feature": False,
"kfold": False,
"train_ratio": 0.7,
"test_ratio": 0.1,
"num_layers": 1,
"dropout": 0.5,
"batch_size": 20,
"target": 0,
"task": "unsupervised_graph_classification",
"model": "infograph",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.001,
"weight_decay": 5e-4,
"max_epoch": 500,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [0, 1, 2],
"dropout": 0.1,
"hidden_size": 64,
"alpha": 0.5,
"num_layers": 2,
"activation": "relu",
"nprop_inference": 2,
"norm": "sym",
"eps": 1e-4,
"k": 32,
"eval_step": 5,
"batch_size": 1024,
"test_batch_size": 10240,
"task": "node_classification",
"model": "pprgo",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_graph_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.001,
"weight_decay": 5e-4,
"max_epoch": 500,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [0],
"hidden_size": 32,
"degree_feature": False,
"gamma": 0.5,
"kfold": False,
"uniform_feature": False,
"train_ratio": 0.7,
"test_ratio": 0.1,
"dropout": 0.5,
"batch_size": 20,
"sample": 30,
"stride": 1,
"neighbor": 10,
"iteration": 5,
"task": "graph_classification",
"model": "patchy_san",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.00005,
"weight_decay": 5e-4,
"max_epoch": 500,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [0, 1, 2],
"num_features": 1,
"hidden_size": 2048,
"out_channels": 1,
"num_propagations": 3,
"num_layers": 3,
"dropout": 0.5,
"directed": False,
"dropedge_rate": 0.2,
"asymm_norm": False,
"set_diag": False,
"remove_diag": False,
"task": "node_classification",
"model": "sign",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_graph_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"hidden_size": 128,
"dropout": 0.0,
"pooling": 0.5,
"batch_size": 64,
"train_ratio": 0.8,
"test_ratio": 0.1,
"lr": 0.001,
"weight_decay": 0.001,
"patience": 100,
"max_epoch": 500,
"sample_neighbor": True,
"sparse_attention": True,
"structure_learning": True,
"cpu": cpu,
"device_id": [0],
"seed": [777],
"task": "graph_classification",
"model": "hgpsl",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def get_default_args():
cuda_available = torch.cuda.is_available()
default_dict = {
"hidden_size": 16,
"dropout": 0.5,
"patience": 100,
"max_epoch": 500,
"cpu": not cuda_available,
"lr": 0.01,
"device_id": [0],
"weight_decay": 5e-4,
"missing_rate": -1,
}
default_dict = get_extra_args(default_dict)
return build_args_from_dict(default_dict)
def build_default_args_for_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.01,
"weight_decay": 5e-4,
"max_epoch": 500,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [42],
"task": "node_classification",
"model": "dropedge_gcn",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_multiplex_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"hidden_size": 64,
"cpu": cpu,
"device_id": [0],
"enhance": None,
"save_dir": ".",
"seed": [0, 1, 2],
"epoch": 0,
"load_path": "./saved/gcc_pretrained.pth",
"task": "multiplex_node_classification",
"model": "gcc",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_heterogeneous_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"hidden_size": 128,
"patience": 100,
"max_epoch": 500,
"cpu": cpu,
"device_id": [0],
"lr": 0.005,
"weight_decay": 0.001,
"seed": [0, 1, 2],
"num_layers": 2,
"task": "heterogeneous_node_classification",
"model": "han",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.01,
"weight_decay": 5e-4,
"max_epoch": 1000,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [0, 1, 2],
"dropout": 0.7,
"layer1_pows": [200, 200, 200],
"layer2_pows": [20, 20, 20],
"task": "node_classification",
"model": "mixhop",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def get_default_args():
cuda_available = torch.cuda.is_available()
default_dict = {
"hidden_size": 16,
"dropout": 0.5,
"patience": 100,
"max_epoch": 500,
"cpu": not cuda_available,
"lr": 0.01,
"device_id": [0],
"weight_decay": 5e-4,
"alpha": 0.05,
"t": 5.0,
"k": 128,
"eps": 0.01,
"gdc_type": "ppr",
}
default_dict = get_extra_args(default_dict)
return build_args_from_dict(default_dict)
def build_default_args_for_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.01,
"weight_decay": 5e-4,
"max_epoch": 500,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [0, 1, 2],
"dropout": 0.5,
"hidden_size": 64,
"num_layers": 2,
"filter_size": 5,
"task": "node_classification",
"model": "chebyshev",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.01,
"weight_decay": 5e-4,
"max_epoch": 500,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [0, 1, 2],
"dropout": 0.5,
"hidden_size": 64,
"propagation_type": "appnp", # can also be 'ppnp'
"alpha": 0.1,
"num_iterations": 10,
"task": "node_classification",
"model": "ppnp",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.005,
"weight_decay": 5e-4,
"max_epoch": 1000,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [
72,
],
"dropout": 0.6,
"hidden_size": 8,
"alpha": 0.2,
"nheads": 8,
"task": "node_classification",
"model": "gat",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_node_classification(dataset,
missing_rate=0,
num_layers=40):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.005,
"weight_decay": 5e-4,
"max_epoch": 1000,
"patience": 1000,
"cpu": cpu,
"device_id": [0],
"seed": [0, 1, 2, 3, 4],
"missing_rate": missing_rate,
"norm_mode": "PN",
"norm_scale": 10,
"dropout": 0.6,
"num_layers": num_layers,
"task": "node_classification",
"model": "sgcpn",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)
def build_default_args_for_node_classification(dataset):
cpu = not torch.cuda.is_available()
args = {
"lr": 0.01,
"weight_decay": 5e-4,
"max_epoch": 1000,
"max_epochs": 1000,
"patience": 100,
"cpu": cpu,
"device_id": [0],
"seed": [42],
"dropout": 0.5,
"hidden_size": 256,
"num_layers": 32,
"lmbda": 0.5,
"wd1": 0.001,
"wd2": 5e-4,
"alpha": 0.1,
"task": "node_classification",
"model": "gcnii",
"dataset": dataset,
}
args = get_extra_args(args)
return build_args_from_dict(args)