When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (17) · 18377-18384
DOI: 10.1609/aaai.v39i17.34022 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Ming Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 46-mal zitiert (Crossref).
Abstract (Originalsprache)
Hypergraph neural networks (HNNs) have shown promise in handling tasks characterized by high-order correlations, achieving notable success across various applications. However, there has been limited focus on heterophilic hypergraph learning (HHL), in contrast to the increasing attention given to graph neural networks designed for graphs exhibiting heterophily. This paper aims to pave the way for HHL by addressing key gaps from multiple perspectives: measurement, dataset diversity, and baseline model development. First, we introduce metrics to quantify heterophily in hypergraphs, providing a numerical basis for assessing the homophily/heterophily ratio. Second, we develop diverse benchmark datasets across various real-world scenarios, facilitating comprehensive evaluations of existing HNNs and advancing research in HHL. Additionally, as a novel baseline model, we propose HyperUFG, a framelet-based HNN integrating both low-pass and high-pass filters. Extensive experiments conducted on synthetic and benchmark datasets highlight the challenges current HNNs face with heterophilic hypergraphs, while showcasing that HyperUFG performs competitively and often outperforms many existing models in such scenarios. Overall, our study underscores the urgent need for further exploration and development in this emerging field, with the potential to inspire and guide future research in HHL.
Zitieren
APA
Li, M., Gu, Y., Wang, Y., Fang, Y., Bai, L., Zhuang, X., & Liò, P. (2025). When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline. Proceedings of the AAAI Conference on Artificial Intelligence, 39(17), 18377-18384. https://doi.org/10.1609/aaai.v39i17.34022
Vancouver
Li M, Gu Y, Wang Y, Fang Y, Bai L, Zhuang X, et al. When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(17):18377-18384. doi:10.1609/aaai.v39i17.34022
BibTeX
@article{Li2025,
author = {Li, Ming and Gu, Yongchun and Wang, Yi and Fang, Yujie and Bai, Lu and Zhuang, Xiaosheng and Liò, Pietro},
title = {When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {17},
pages = {18377--18384},
doi = {10.1609/aaai.v39i17.34022}
}
EUVIMED