HyGEN: Regularizing Negative Hyperedge Generation for Accurate Hyperedge Prediction
This work addresses hyperedge prediction, a fundamental task in network analysis, by improving negative sampling to enhance model accuracy, representing an incremental advancement in the field.
The paper tackles the data sparsity problem in hyperedge prediction by proposing HyGEN, a method that generates realistic negative hyperedges with guidance from positive ones and uses regularization to avoid false negatives, achieving consistent outperformance over four state-of-the-art methods on six real-world hypergraphs.
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.