AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

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

Qisen Chai, Yansong Wang, Junjie Huang, Tao Jia

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Graph neural network robustness · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add reward network shaping to RDA training (ablation)Cutter RDA · RDA trainingaverage return: 0.513 -> 0.668Improved
use Cutter instead of GEC at moderate compressionCiteseer rho=0.5 · Citeseer RPSRPS: 0.958 -> 0.963No clear effect
use Cutter instead of MCGS at rho=0.5Citeseer · Citeseer RPSRPS: 0.966 -> 0.963Hurt
use Cutter instead of GEC at extreme compressionCoauthor-Physics rho=0.1 · Coauthor-Physics RPSRPS: 0.497 -> 0.758Improved
use Cutter instead of SparRL at extreme compressionCoauthor-Physics rho=0.1 · Coauthor-Physics RPSRPS: 0.512 -> 0.758Improved
use Cutter instead of GEC for path length at rho=0.5Cora topology · Cora topologypath length difference: 1.045 -> 0.317Improved
use Cutter instead of HySamp for degree differenceCora topology · Cora topologydegree difference: 0.145 -> 0.167Hurt
increase compression from rho=0.5 to rho=0.1 for CutterCutter on Cora · Cora RPSRPS: 0.953 -> 0.832Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy