EUVIMEDEUVIMED entdecken
Crossref

Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation

Qisen Chai, Yansong Wang, Junjie Huang, Tao Jia

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (17) · 14529-14537

DOI: 10.1609/aaai.v40i17.38470 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Qisen Chai und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As graph-structured data grow increasingly large, evaluating their robustness under adversarial attacks becomes computationally expensive and difficult to scale. To address this challenge, we propose to compress graphs into compact representations that preserve both topological structure and robustness profile, enabling efficient and reliable evaluation.We propose Cutter, a dual-agent reinforcement learning framework composed of a Vital Detection Agent (VDA) and a Redundancy Detection Agent (RDA), which collaboratively identify structurally vital and redundant nodes for guided compression. Cutter incorporates three key strategies to enhance learning efficiency and compression quality: trajectory-level reward shaping to transform sparse trajectory returns into dense, policy-equivalent learning signals; prototype-based shaping to guide decisions using behavioral patterns from both highand low-return trajectories; and cross-agent imitation to enable safer and more transferable exploration. Experiments on multiple real-world graphs demonstrate that Cutter generates compressed graphs that retain essential static topological properties and exhibit robustness degradation trends highly consistent with the original graphs under various attack scenarios, thereby significantly improving evaluation efficiency without compromising assessment fidelity.

Zitieren

APA

Chai, Q., Wang, Y., Huang, J., & Jia, T. (2026). Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(17), 14529-14537. https://doi.org/10.1609/aaai.v40i17.38470

Vancouver

Chai Q, Wang Y, Huang J, Jia T. Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(17):14529-14537. doi:10.1609/aaai.v40i17.38470

BibTeX
@article{Chai2026,
  author = {Chai, Qisen and Wang, Yansong and Huang, Junjie and Jia, Tao},
  title = {Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {17},
  pages = {14529--14537},
  doi = {10.1609/aaai.v40i17.38470}
}
Kostenlos starten →