EUVIMEDEUVIMED entdecken
Crossref

HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning

Qirui Ji, Bin Qin, Yifan Jin, Yunze Zhao, Chuxiong Sun, Changwen Zheng, Jianwen Cao, Jiangmeng Li

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (26) · 22209-22218

DOI: 10.1609/aaai.v40i26.39377 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Qirui Ji und 7 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph contrastive learning (GCL) aims to learn discriminative semantic invariance by contrasting different views of the same graph that share critical topological patterns. However, existing GCL approaches with structural augmentations often struggle to identify task-relevant topological structures, let alone adapt to the varying coarse-to-fine topological granularities required across different downstream tasks. To remedy this issue, we introduce Hierarchical Topological Granularity Graph Contrastive Learning (HTG-GCL), a novel framework that leverages transformations of the same graph to generate multi-scale ring-based cellular complexes, embodying the concept of topological granularity, thereby generating diverse topological views. Recognizing that a certain granularity may contain misleading semantics, we propose a multi-granularity decoupled contrast and apply a granularity-specific weighting mechanism based on uncertainty estimation. Comprehensive experiments on various benchmarks demonstrate the effectiveness of HTG-GCL, highlighting its superior performance in capturing meaningful graph representations through hierarchical topological information.

Zitieren

APA

Ji, Q., Qin, B., Jin, Y., Zhao, Y., Sun, C., Zheng, C., Cao, J., & Li, J. (2026). HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(26), 22209-22218. https://doi.org/10.1609/aaai.v40i26.39377

Vancouver

Ji Q, Qin B, Jin Y, Zhao Y, Sun C, Zheng C, et al. HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(26):22209-22218. doi:10.1609/aaai.v40i26.39377

BibTeX
@article{Ji2026,
  author = {Ji, Qirui and Qin, Bin and Jin, Yifan and Zhao, Yunze and Sun, Chuxiong and Zheng, Changwen and Cao, Jianwen and Li, Jiangmeng},
  title = {HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {26},
  pages = {22209--22218},
  doi = {10.1609/aaai.v40i26.39377}
}
Kostenlos starten →