Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning
This work addresses limitations in heterogeneous graph analysis for researchers and practitioners, offering a more flexible framework, though it is incremental as it builds on existing GNN and HGNN approaches.
The paper tackles the problem of coarse-grained, domain-specific meta-paths in heterogeneous graph representation learning by introducing MF2Vec, which uses fine-grained multi-facet paths via random walks, resulting in improved performance over existing methods in tasks like classification and link prediction.
Recent advancements in graph neural networks (GNNs) and heterogeneous GNNs (HGNNs) have advanced node embeddings and relationship learning for various tasks. However, existing methods often rely on domain-specific predefined meta-paths, which are coarse-grained and focus solely on aspects like node type, limiting their ability to capture complex interactions. We introduce MF2Vec, a model that uses multi-faceted (fine-grained) paths instead of predefined meta-paths. MF2Vec extracts paths via random walks and generates multi-faceted vectors, ignoring predefined schemas. This method learns diverse aspects of nodes and their relationships, constructs a homogeneous network, and creates node embeddings for classification, link prediction, and clustering. Extensive experiments show that MF2Vec outperforms existing methods, offering a more flexible and comprehensive framework for analyzing complex networks. The code is available at https://anonymous.4open.science/r/MF2Vec-6ABC.