EUVIMEDEUVIMED entdecken
Crossref

CEGOOD: Community Enhanced Graph Out-of-Distribution Detection

Xinlei Wang, Bin Yu, Chen Zhang, Wenjie Mao, Yu Xie, Limei Peng, Pin-Han Ho

IEEE Transactions on Big Data · 2026-08 · 12 (4) · 1233-1248

DOI: 10.1109/tbdata.2026.3673392 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Big Data, 2026-08. Verfasst von Xinlei Wang und 6 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Gefördert von: Key Research and Development Projects of Shaanxi Province, National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph Neural Networks (GNNs) often suffer from degraded performance when encountering out-of-distribution (OOD) samples, particularly in multi-domain graph scenarios. Existing graph OOD detection methods typically require extensive modifications to data or model architectures, resulting in high computational costs and limited generalization. Moreover, prior approaches largely overlook local structural semantics and community-level patterns, leading to biased representations and suboptimal detection performance. To overcome these limitations, we propose community enhanced graph out-of-distribution detection (CEGOOD), a novel framework that incorporates community structure into GNN-based OOD detection. Specifically, we propose two community-aware view generation strategies: intra-community attribute aggregation (ICAA) to distill fine-grained feature coherence and inter-community edge dropping (ICED) to fortify structural robustness by pruning non-critical cross-community edges. Furthermore, We also design three community-level loss functions (compactness, separability, and balance) to optimize community hierarchical structures and improve community representation. Experimental results on various datasets show that CEGOOD outperforms state-of-the-art baselines by an average of 1.8% AUC, with notable gains of 2.4% on AIDS+DHFR and 2.8% on BBBP+BACE, demonstrating superior adaptability and effectiveness in graph OOD detection tasks.

Förderung

  • Key Research and Development Projects of Shaanxi Province
  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Scientific Research Program Funded by Shaanxi Provincial Education Department

Zitieren

APA

Wang, X., Yu, B., Zhang, C., Mao, W., Xie, Y., Peng, L., & Ho, P. (2026). CEGOOD: Community Enhanced Graph Out-of-Distribution Detection. IEEE Transactions on Big Data, 12(4), 1233-1248. https://doi.org/10.1109/tbdata.2026.3673392

Vancouver

Wang X, Yu B, Zhang C, Mao W, Xie Y, Peng L, et al. CEGOOD: Community Enhanced Graph Out-of-Distribution Detection. IEEE Transactions on Big Data. 2026;12(4):1233-1248. doi:10.1109/tbdata.2026.3673392

BibTeX
@article{Wang2026,
  author = {Wang, Xinlei and Yu, Bin and Zhang, Chen and Mao, Wenjie and Xie, Yu and Peng, Limei and Ho, Pin-Han},
  title = {CEGOOD: Community Enhanced Graph Out-of-Distribution Detection},
  journal = {IEEE Transactions on Big Data},
  year = {2026},
  volume = {12},
  number = {4},
  pages = {1233--1248},
  doi = {10.1109/tbdata.2026.3673392}
}
Kostenlos starten →