Prototype-Enhanced Hypergraph Learning for Heterogeneous Information Networks

TL;DR

This paper introduces a prototype-enhanced hypergraph learning method for HINs that captures higher-order relationships and semantic information without relying on predefined metapaths, improving node classification.

Contribution

It presents a novel hypergraph-based approach utilizing prototypes to enhance robustness and interpretability in HIN node classification tasks.

Findings

Outperforms existing methods on three real-world HIN datasets.

Effectively captures higher-order relationships among nodes.

Provides more interpretable insights into network structures.

Abstract

The variety and complexity of relations in multimedia data lead to Heterogeneous Information Networks (HINs). Capturing the semantics from such networks requires approaches capable of utilizing the full richness of the HINs. Existing methods for modeling HINs employ techniques originally designed for graph neural networks, and HINs decomposition analysis, like using manually predefined metapaths. In this paper, we introduce a novel prototype-enhanced hypergraph learning approach for node classification in HINs. Using hypergraphs instead of graphs, our method captures higher-order relationships among nodes and extracts semantic information without relying on metapaths. Our method leverages the power of prototypes to improve the robustness of the hypergraph learning process and creates the potential to provide human-interpretable insights into the underlying network structure. Extensive experiments on three real-world HINs demonstrate the effectiveness of our method.