HyGEN: Regularizing Negative Hyperedge Generation for Accurate Hyperedge Prediction

TL;DR

HyGEN introduces a guided negative hyperedge generator and a regularization technique to improve hyperedge prediction accuracy, effectively addressing data sparsity and false negative issues in hypergraph analysis.

Contribution

The paper presents HyGEN, a novel hyperedge prediction method that uses guided negative hyperedge generation and regularization to enhance prediction accuracy.

Findings

HyGEN outperforms four state-of-the-art methods on six real-world hypergraphs.

The guided negative hyperedge generator produces more realistic negatives.

Regularization prevents false negatives, improving model reliability.

Abstract

Hyperedge prediction is a fundamental task to predict future high-order relations based on the observed network structure. Existing hyperedge prediction methods, however, suffer from the data sparsity problem. To alleviate this problem, negative sampling methods can be used, which leverage non-existing hyperedges as contrastive information for model training. However, the following important challenges have been rarely studied: (C1) lack of guidance for generating negatives and (C2) possibility of producing false negatives. To address them, we propose a novel hyperedge prediction method, HyGEN, that employs (1) a negative hyperedge generator that employs positive hyperedges as a guidance to generate more realistic ones and (2) a regularization term that prevents the generated hyperedges from being false negatives. Extensive experiments on six real-world hypergraphs reveal that HyGEN consistently outperforms four state-of-the-art hyperedge prediction methods.