EUVIMEDEUVIMED entdecken
Crossref

Scalable Semi-supervised Community Search via Graph Transformer on Attributed Heterogeneous Information Networks

Linlin Ding, Zhaosong Zhao, Mo Li, Yishan Pan, Xin Wang, Renata Borovica-Gajic

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (17) · 14666-14674

DOI: 10.1609/aaai.v40i17.38485 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Linlin Ding und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Attributed heterogeneous information networks (AHINs) encode rich semantics through diverse node and edge types. Recent learning-based community search methods on AHINs have shown promising performance but face two major limitations: i) difficulty scaling to large graphs due to memory-intensive neighbor-based propagation (e.g., GNNs and node-level attention), and ii) reliance on explicit community-level labels, which are often unavailable or costly to obtain. To address these issues, we propose a scalable Semi-supervised Community Search framework on AHINs (SCSAH), enabling scalability and efficiency, while eliminating the need for community-level labels by leveraging readily available node classification labels. Specifically, we devise MvSF2Token to extract Multi-view Semantic Features (MvSFs) as compact subgraph-level tokens before training, significantly reducing model propagation complexity. We then design a View-Aware Semantic Graph Transformer (VASGhormer) to effectively encode MvSFs by capturing cross-view dependencies and fusing semantic features. The combination of MvSF2Token and VASGhormer ensures scalability, efficiency, and robust performance. Furthermore, we design a View-Aware Contrastive Learner to train VASGhormer without requiring community-level supervision. Extensive experiments on five real-world datasets show that SCSAH outperforms state-of-the-art methods, achieving 18.06% higher performance and 10.43 times faster training.

Zitieren

APA

Ding, L., Zhao, Z., Li, M., Pan, Y., Wang, X., & Borovica-Gajic, R. (2026). Scalable Semi-supervised Community Search via Graph Transformer on Attributed Heterogeneous Information Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 40(17), 14666-14674. https://doi.org/10.1609/aaai.v40i17.38485

Vancouver

Ding L, Zhao Z, Li M, Pan Y, Wang X, Borovica-Gajic R. Scalable Semi-supervised Community Search via Graph Transformer on Attributed Heterogeneous Information Networks. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(17):14666-14674. doi:10.1609/aaai.v40i17.38485

BibTeX
@article{Ding2026,
  author = {Ding, Linlin and Zhao, Zhaosong and Li, Mo and Pan, Yishan and Wang, Xin and Borovica-Gajic, Renata},
  title = {Scalable Semi-supervised Community Search via Graph Transformer on Attributed Heterogeneous Information Networks},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {17},
  pages = {14666--14674},
  doi = {10.1609/aaai.v40i17.38485}
}
Kostenlos starten →