Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs

TL;DR

This paper introduces LFH, a dynamic hypergraph learning framework that leverages heterogeneity attributes for improved node classification and link prediction, demonstrating significant performance gains over existing methods.

Contribution

The paper presents a novel hypergraph learning framework with dynamic hyperedge construction and attentive embedding updates based on graph heterogeneity.

Findings

Achieved an average 12.5% improvement in node classification accuracy.

Achieved an average 13.3% improvement in link prediction performance.

Demonstrated effectiveness across multiple datasets and models.

Abstract

Graph neural network (GNN) has gained increasing popularity in recent years owing to its capability and flexibility in modeling complex graph structure data. Among all graph learning methods, hypergraph learning is a technique for exploring the implicit higher-order correlations when training the embedding space of the graph. In this paper, we propose a hypergraph learning framework named LFH that is capable of dynamic hyperedge construction and attentive embedding update utilizing the heterogeneity attributes of the graph. Specifically, in our framework, the high-quality features are first generated by the pairwise fusion strategy that utilizes explicit graph structure information when generating initial node embedding. Afterwards, a hypergraph is constructed through the dynamic grouping of implicit hyperedges, followed by the type-specific hypergraph learning process. To evaluate the effectiveness of our proposed framework, we conduct comprehensive experiments on several popular datasets with eleven state-of-the-art models on both node classification and link prediction tasks, which fall into categories of homogeneous pairwise graph learning, heterogeneous pairwise graph learning, and hypergraph learning. The experiment results demonstrate a significant performance gain (average 12.5% in node classification and 13.3% in link prediction) compared with recent state-of-the-art methods.