EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

S2-HGNN: Scale-Aware Hypergraph Node Classification with Spectral Inductive Bias

Jiangnan Zhou, Sheng Zhang, Bing Wu, Qiuming Wang, Chennan Wu, Ziqiang Luo, Ka Sun, Hongmei Mao

Entropy · 26.05.2026 · 28 (6) · 592

DOI: 10.3390/e28060592 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 26.05.2026. Verfasst von Jiangnan Zhou und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing methods for hypergraph node classification usually rely on local message passing and use a unified strategy for topological modeling across hyperedges of different sizes. However, they have two limitations in semi-supervised settings. First, representation learning mainly depends on local neighborhoods, making it difficult to incorporate global topological information. Second, a unified structural modeling strategy cannot effectively handle both small and large hyperedges. Small hyperedges require modeling fine-grained local relations, while large hyperedges need sparse group-level structure. To address these issues, we propose S2-HGNN, a scale-aware hypergraph node classification framework with spectral inductive bias for semi-supervised learning. S2-HGNN first injects global topological information into the input features using complementary hypergraph spectral operators. It then constructs different auxiliary topologies based on hyperedge size. For small hyperedges, it uses Top-k constrained clique expansion to preserve representative local relations. For large hyperedges, it uses star expansion to reduce redundant connections while preserving sparse group-level structure. Finally, node representations are jointly learned from the original hypergraph backbone and the two auxiliary branches, and final predictions are obtained through node-level adaptive fusion. Experiments on multiple public datasets show that the proposed method consistently outperforms strong baselines and exhibits superior robustness under feature perturbations.

Schlagwörter

Stichwörter der Autor:innen

adaptive fusionhypergraph node classificationscale-aware modelingsemi-supervised learningspectral inductive bias

Autor:innen und Institutionen

  • School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhou, J., Zhang, S., Wu, B., Wang, Q., Wu, C., Luo, Z., Sun, K., & Mao, H. (2026). S2-HGNN: Scale-Aware Hypergraph Node Classification with Spectral Inductive Bias. Entropy, 28(6), 592. https://doi.org/10.3390/e28060592

Vancouver

Zhou J, Zhang S, Wu B, Wang Q, Wu C, Luo Z, et al. S2-HGNN: Scale-Aware Hypergraph Node Classification with Spectral Inductive Bias. Entropy. 2026;28(6):592. doi:10.3390/e28060592

BibTeX
@article{Zhou2026,
  author = {Zhou, Jiangnan and Zhang, Sheng and Wu, Bing and Wang, Qiuming and Wu, Chennan and Luo, Ziqiang and Sun, Ka and Mao, Hongmei},
  title = {S2-HGNN: Scale-Aware Hypergraph Node Classification with Spectral Inductive Bias},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {6},
  pages = {592},
  doi = {10.3390/e28060592}
}
Kostenlos starten →