EUVIMEDEUVIMED entdecken
Crossref

Structural Entropy Based Graph Structure Learning for Node Classification

Liang Duan, Xiang Chen, Wenjie Liu, Daliang Liu, Kun Yue, Angsheng Li

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (8) · 8372-8379

DOI: 10.1609/aaai.v38i8.28679 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Liang Duan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As one of the most common tasks in graph data analysis, node classification is frequently solved by using graph structure learning (GSL) techniques to optimize graph structures and learn suitable graph neural networks. Most of the existing GSL methods focus on fusing different structural features (basic views) extracted from the graph, but very little graph semantics, like hierarchical communities, has been incorporated. Thus, they might be insufficient when dealing with the graphs containing noises from real-world complex systems. To address this issue, we propose a novel and effective GSL framework for node classification based on the structural information theory. Specifically, we first prove that an encoding tree with the minimal structural entropy could contain sufficient information for node classification and eliminate redundant noise via the graph's hierarchical abstraction. Then, we provide an efficient algorithm for constructing the encoding tree to enhance the basic views. Combining the community influence deduced from the encoding tree and the prediction confidence of each view, we further fuse the enhanced views to generate the optimal structure. Finally, we conduct extensive experiments on a variety of datasets. The results demonstrate that our method outperforms the state-of-the-art competitors on effectiveness and robustness.

Zitieren

APA

Duan, L., Chen, X., Liu, W., Liu, D., Yue, K., & Li, A. (2024). Structural Entropy Based Graph Structure Learning for Node Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 38(8), 8372-8379. https://doi.org/10.1609/aaai.v38i8.28679

Vancouver

Duan L, Chen X, Liu W, Liu D, Yue K, Li A. Structural Entropy Based Graph Structure Learning for Node Classification. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(8):8372-8379. doi:10.1609/aaai.v38i8.28679

BibTeX
@article{Duan2024,
  author = {Duan, Liang and Chen, Xiang and Liu, Wenjie and Liu, Daliang and Yue, Kun and Li, Angsheng},
  title = {Structural Entropy Based Graph Structure Learning for Node Classification},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {8},
  pages = {8372--8379},
  doi = {10.1609/aaai.v38i8.28679}
}
Kostenlos starten →