PlanetAlign.algorithms.WLAlign

class WLAlign(emb_dim: int = 128, struct_lr: float = 0.005, batch_size: int = 1000, neg_sample_size: int = 20, dtype: dtype = torch.float32)[source]

Bases: BaseModel

Embedding-based method WLAlign for pairwise plain network alignment. WLAlign is proposed by the paper “WL-Align: Weisfeiler-Lehman Relabeling for Aligning Users Across Networks via Regularized Representation Learning.” in TKDE 2023.

Parameters:

  • emb_dim (int, optional) – The dimension of the node embeddings. Default is 128.

  • struct_lr (float, optional) – The learning rate for the structural model. Default is 5e-3.

  • batch_size (int, optional) – The batch size for training. Default is 1000.

  • neg_sample_size (int, optional) – The number of negative samples for training. Default is 20.

  • dtype (torch.dtype, optional) – Data type of the tensors, choose from torch.float32 or torch.float64. Default is torch.float32.

test(dataset: Dataset, gids: List[int] | Tuple[int, ...], metrics: tuple[str] | list[str] = None)
Parameters:

  • dataset (Dataset) – The dataset containing the graphs to be aligned and the training/test data.

  • gids (list[int] or tuple[int, ...]) – The indices of the graphs in the dataset to be aligned.

  • metrics (tuple[str] or list[str], optional) – The metrics to be computed after alignment. Default is None, which computes Hits@K (K=1, 10, 30, 50) and MRR metrics.

train(dataset: Dataset, gid1: int, gid2: int, use_attr: bool = False, total_epochs: int = 50, struct_epochs: int = 100, save_log: bool = True, verbose: bool = True)[source]
Parameters:

  • dataset (Dataset) – The dataset containing the graphs to be aligned and the training/test data.

  • gid1 (int) – The index of the first graph in the dataset to be aligned.

  • gid2 (int) – The index of the second graph in the dataset to be aligned.

  • use_attr (bool, optional) – Whether to use node and edge attributes for alignment. Default is False.

  • total_epochs (int, optional) – The maximum number of epochs for the optimization. Default is 50.

  • struct_epochs (int, optional) – The number of epochs for the structural model training. Default is 100.

  • save_log (bool, optional) – Whether to save the evaluation logs. Default is True.

  • verbose (bool, optional) – Whether to print the progress during training. Default is True.