Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning

📅 2024-07-30
🏛️ arXiv.org
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Existing heterogeneous graph representation learning methods rely heavily on predefined, coarse-grained meta-paths and struggle to capture fine-grained semantic relationships. To address this, we propose MF2Vec, an unsupervised framework that eliminates manual schema design. Its core innovation lies in a multi-faceted path modeling mechanism: adaptive random walks automatically discover hierarchical semantic paths between nodes, yielding multi-faceted node embeddings; subsequently, homogeneous subgraphs are reconstructed to enable compatibility with shallow embedding techniques (e.g., DeepWalk variants). Evaluated on multiple benchmark datasets, MF2Vec consistently outperforms HGNN-based baselines across node classification, link prediction, and clustering tasks, achieving average improvements of 3.2%–7.8%. The framework offers schema-free flexibility while maintaining strong generalization capability.

Technology Category

Application Category

📝 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.
Problem

Research questions and friction points this paper is trying to address.

Graph Neural Networks
Heterogeneous Graphs
Complex Node Relationships
Innovation

Methods, ideas, or system contributions that make the work stand out.

MF2Vec
Multi-faceted Paths
Complex Network Analysis
🔎 Similar Papers
No similar papers found.
J
JongWoo Kim
Korea Advanced Institute of Science and Technology (KAIST), Korea
S
SeongYeub Chu
Korea Advanced Institute of Science and Technology (KAIST), Korea
H
HyeongMin Park
Korea Advanced Institute of Science and Technology (KAIST), Korea
B
Bryan Wong
Korea Advanced Institute of Science and Technology (KAIST), Korea
M
MunYong Yi
Korea Advanced Institute of Science and Technology (KAIST), Korea