{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:50:22Z","timestamp":1773802222530,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"17","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.1609\/aaai.v40i17.38470","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:30:41Z","timestamp":1773793841000},"page":"14529-14537","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation"],"prefix":"10.1609","volume":"40","author":[{"given":"Qisen","family":"Chai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yansong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38470\/42432","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38470\/42432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:30:41Z","timestamp":1773793841000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38470"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i17.38470","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}