aiqbench analysis
AutoHGNN advances the field of hypergraph learning by introducing a specialized neural architecture search framework that automates structure design while preserving complex higher-order relations. By integrating a Hyper-Interaction Module and a novel stability metric, the method outperforms manual baselines in both accuracy and efficiency, addressing key limitations in current graph-based models. This work represents a significant step toward more adaptable and robust AI systems capable of handling intricate data topologies.
AutoHGNN: Robust and Efficient Neural Architecture Search for Hypergraph Neural Networks
arXiv:2609.33392v1 Announce Type: new Abstract: Hypergraph neural networks have achieved significant success in recent years. However, manual architecture crafting is labor-intensive and often fails to capture complex, higher-order relations, making the automation of hypergraph neural network structure design crucial. To improve the automation and adaptability of hypergraph learning, this paper proposes AutoHGNN, a neural architecture search framework tailored for hypergraph neural networks. First, we introduce a Hyper-Interaction Module (HIM) into the search space to address the mismatch between conventional graph neural network designs and hypergraph data. Second, we propose Hypergraph Stable Topological Distance (HyperSTD) as a structural selection criterion to identify architectures that best preserve the intrinsic structural affinities of the original hypergraph during differentiable search. Extensive experiments on various benchmark datasets demonstrate that AutoHGNN consistently outperforms manually designed and automatically searched baselines in classification accuracy and time efficiency, proving that the discovered architectures are significantly more effective.
Abstract:Hypergraph neural networks have achieved significant success in recent years. However, manual architecture crafting is labor-intensive and often fails to capture complex, higher-order relations, making the automation of hypergraph neural network structure design crucial. To improve the automation and adaptability of hypergraph learning, this paper proposes AutoHGNN, a neural architecture search framework tailored for hypergraph neural networks. First, we introduce a Hyper-Interaction Module (HIM) into the search space to address the mismatch between conventional graph neural network designs and hypergraph data. Second, we propose Hypergraph Stable Topological Distance (HyperSTD) as a structural selection criterion to identify architectures that best preserve the intrinsic structural affinities of the original hypergraph during differentiable search. Extensive experiments on various benchmark datasets demonstrate that AutoHGNN consistently outperforms manually designed and automatically searched baselines in classification accuracy and time efficiency, proving that the discovered architectures are significantly more effective.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2609.33392 [cs.LG]
(or arXiv:2609.33392v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.33392 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1016/j.knosys.2026.116609 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 250 words
Related coverage
From Diffusion to Reaction-Diffusion: A Dynamical-Systems View of Oversmoothing in Hypergraph Neural Networks
arXiv · Jul 20, 2026
[AINews] not much happened today
Latent Space · Sep 10, 2026
PIRAMID: Progress and Plans
LessWrong · Jul 27, 2026
FENAS: A Few-Shot Meta-Ensembling Framework for Efficient Neural Architecture Search with Synergized Zero-Cost Proxies
arXiv · Oct 14, 2026