Towards Trustworthy Hypergraph Neural Networks under Label Noise

2026-08-04

AI Summary

Label noise significantly degrades the performance of hypergraph neural networks, yet existing robust learning methods struggle to effectively handle the interplay between high-order relationships and noisy labels in hypergraphs. This work addresses this challenge by establishing the first unified benchmark for evaluating robustness in hypergraph node classification under label noise and introduces HyperTrust, a novel framework that dynamically refines hypergraph structure. HyperTrust estimates hyperedge credibility through a pretraining phase coupled with an entropy-aware mechanism, then jointly applies HyperedgeBoost to reinforce reliable connections and HyperedgePrune to suppress noise propagation. Extensive experiments demonstrate that HyperTrust consistently outperforms state-of-the-art methods across diverse datasets and noise settings, achieving superior accuracy and robustness, thereby laying a foundational approach for robust learning on hypergraphs.

Abstract

Hypergraph neural networks (HGNNs) have demonstrated remarkable capabilities in processing complex higher-order relationships. However, their performance is highly dependent on labeled data, making them vulnerable to label noise. Despite advances in learning with label noise (LLN) and graph learning with label noise (GLN), noisy-label learning on hypergraphs remains underexplored. In this paper, we present a systematic study of hypergraph node classification under label noise. First, we adapt representative LLN and GLN methods to hypergraphs and evaluate them under a unified benchmark, revealing the limitations of existing robust learning strategies for hypergraphs. Building on this, we propose a new hypergraph robust framework, HyperTrust, which first estimates hyperedge trustworthiness through a pretraining-based, entropy-aware strategy, and then incorporates the HyperedgeBoost module to enhance reliable supervision by connecting unlabeled nodes to trustworthy hyperedges, as well as the HyperedgePrune module to suppress noisy propagation by removing untrustworthy node-hyperedge incidences. Finally, two modules work collaboratively to adjust the hypergraph structure and generate final predictions. Extensive experiments and theoretical analysis demonstrate the effectiveness and robustness of HyperTrust on multiple hypergraph datasets under various noisy settings. Our work provides a unified benchmark and an effective solution for hypergraph learning with label noise and lays a foundation for future research in this direction.

Problem

• hypergraph neural networks
• label noise
• node classification
• trustworthy learning
• noisy-label learning

Innovation

• Hypergraph Neural Networks
• Label Noise
• Trustworthy Learning
• Hyperedge Trustworthiness
• Robust Graph Learning