AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Promoting Generalization for Exact Combinatorial Solvers via Adversarial Instance Augmentation

Haoyang Liu, Jie Wang, Yufei Kuang, Xijun Li, Yongdong Zhang, Feng Wu

TPAMI 2026 · Reinforcement learning › Visual and representation RL · approach: RL with tree search for discovery · 13 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 adversarial instance augmentation to GNN branching (AdaSolver-IL)GNN · Set Covering D1solving time: 9.25 -> 6.28Improved
add adversarial instance augmentation to GNN branching (AdaSolver-IL)GNN · easier distributions, four benchmarkssolving time: 24.60% improvement of solving timeImproved
add adversarial instance augmentation to tMDP+DFS (AdaSolver-RL)tMDP+DFS · easier distributions, four benchmarkssolving time: 10.75% improvementImproved
add adversarial instance augmentation to GNN branching on larger instancesGNN · harder distributions D4-D6PD integral: 9.53% over GNN and 11.68% over tMDP+DFSImproved
add AdaSolver-IL on real-world Anonymous datasetGNN · Anonymous (MIRPLIB)PD gap: 1.10 -> 0.92Improved
train GNN on 100 instead of 10000 instancesGNN · four benchmarkssolving time: 115.58% increase in solving time and 25.57% increase in PD integralHurt
add AdaSolver-IL with only 100 training instancesGNN (100 instances) · low-data trainingsolving time: 36.20% improvement in solving time and 16.94% in PD integralImproved
replace adversarial augmentation policy with random masking (IL), i.e. adding adversarial policy (ablation)AdaSolver-IL · Set Covering D4PD integral: 15550.73 -> 10691.05Improved
add adversarial policy instead of random masking (IL) (ablation)AdaSolver-IL · Set Covering D1solving time: 6.13 vs 6.28No clear effect
add adversarial policy instead of random masking (RL) (ablation)AdaSolver-RL · Capacitated Facility Location D4PD integral: 8579.21 -> 7779.28Improved
raise masking proportion from 0.01 to 0.05 (ablation)AdaSolver-IL · Set Covering D1solving time: 6.28 -> 9.20Hurt
set beta to 0.1 instead of 0.01 (ablation)AdaSolver-IL · Combinatorial Auctions D2solving time: 16.34 -> 23.84Hurt

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