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.
@article{arxiv.2407.20648,
title = {Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning},
author = {Jongwoo Kim and Seongyeub Chu and Hyeongmin Park and Bryan Wong and Keejun Han and Mun Yong Yi},
journal= {arXiv preprint arXiv:2407.20648},
year = {2025}
}