Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning

TL;DR

MF2Vec introduces a flexible approach for heterogeneous graph representation learning by utilizing multi-faceted paths through random walks, surpassing traditional meta-path methods in capturing complex node interactions.

Contribution

It proposes MF2Vec, a novel model that leverages multi-faceted paths instead of predefined meta-paths for richer node and relationship embeddings.

Findings

MF2Vec outperforms existing methods in various tasks.

The approach captures complex interactions better than meta-path-based methods.

Extensive experiments validate the effectiveness of MF2Vec.

Abstract

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.