Scalable and Effective Negative Sample Generation for Hyperedge Prediction

TL;DR

This paper introduces SEHP, a scalable framework using diffusion models and boundary-aware loss to generate high-quality negative samples for hyperedge prediction, significantly improving accuracy and efficiency.

Contribution

SEHP is the first to integrate diffusion models with boundary-aware loss for negative sample generation in hyperedge prediction, enhancing scalability and global pattern capturing.

Findings

SEHP outperforms existing methods in accuracy.

SEHP achieves higher efficiency and scalability.

The approach preserves accuracy while operating in latent space.

Abstract

Hyperedge prediction is crucial in hypergraph analysis for understanding complex multi-entity interactions in various web-based applications, including social networks and e-commerce systems. Traditional methods often face difficulties in generating high-quality negative samples due to the imbalance between positive and negative instances. To address this, we present the Scalable and Effective Negative Sample Generation for Hyperedge Prediction (SEHP) framework, which utilizes diffusion models to tackle these challenges. SEHP employs a boundary-aware loss function that iteratively refines negative samples, moving them closer to decision boundaries to improve classification performance. SEHP samples positive instances to form sub-hypergraphs for scalable batch processing. By using structural information from sub-hypergraphs as conditions within the diffusion process, SEHP effectively captures global patterns. To enhance efficiency, our approach operates directly in latent space, avoiding the need for discrete ID generation and resulting in significant speed improvements while preserving accuracy. Extensive experiments show that SEHP outperforms existing methods in accuracy, efficiency, and scalability, representing a substantial advancement in hyperedge prediction techniques. Our code is available here.