Metraipolis › archive › dc_047d09a40a0a
AutoHGNN: Robust and Efficient Neural Architecture Search for Hypergraph Neural Networks — arXiv:2609.33392
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33392
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:01:23.111Z
- SHA-256 of the archived text
66e3b0c0c2ccb605cb0758a4f732a527e2784ee9fc739be6530ca6f4c252ffa4- Stable URL of this page
https://metraipolis.com/documento/dc_047d09a40a0a
How to cite
AutoHGNN: Robust and Efficient Neural Architecture Search for Hypergraph Neural Networks — arXiv:2609.33392 — arXiv (en), https://arxiv.org/abs/2609.33392 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_047d09a40a0a (Metraipolis archive dc_047d09a40a0a, sha256 66e3b0c0c2ccb605cb0758a4f732a527e2784ee9fc739be6530ca6f4c252ffa4)
BibTeX
@misc{dc047d09a40a0a,
title = {AutoHGNN: Robust and Efficient Neural Architecture Search for Hypergraph Neural Networks — arXiv:2609.33392},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33392},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_047d09a40a0a; sha256 66e3b0c0c2ccb605cb0758a4f732a527e2784ee9fc739be6530ca6f4c252ffa4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33392. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.33392 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:02.636Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).