Ada-HGNN: Adaptive Sampling for Scalable Hypergraph Neural Networks

TL;DR

This paper introduces Ada-HGNN, an adaptive sampling method for hypergraph neural networks that significantly enhances scalability and efficiency while preserving performance, enabling broader application in large-scale complex data scenarios.

Contribution

We propose a novel adaptive sampling strategy, along with RHA and MLP modules, to improve the scalability and robustness of hypergraph neural networks.

Findings

Reduces computational and memory costs substantially.

Maintains comparable performance to traditional HGNNs.

Demonstrates effectiveness on real-world datasets.

Abstract

Hypergraphs serve as an effective model for depicting complex connections in various real-world scenarios, from social to biological networks. The development of Hypergraph Neural Networks (HGNNs) has emerged as a valuable method to manage the intricate associations in data, though scalability is a notable challenge due to memory limitations. In this study, we introduce a new adaptive sampling strategy specifically designed for hypergraphs, which tackles their unique complexities in an efficient manner. We also present a Random Hyperedge Augmentation (RHA) technique and an additional Multilayer Perceptron (MLP) module to improve the robustness and generalization capabilities of our approach. Thorough experiments with real-world datasets have proven the effectiveness of our method, markedly reducing computational and memory demands while maintaining performance levels akin to conventional HGNNs and other baseline models. This research paves the way for improving both the scalability and efficacy of HGNNs in extensive applications. We will also make our codebase publicly accessible.