AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

MILPnet: A Multi-Scale Architecture with Geometric Feature Sequence Representations for Advancing MILP Problems

Ruobing Wang, Xin Li, Mingzhong Wang

ICLR 2026 · Graph learning › Graph algorithms and clustering · approach: Neural combinatorial optimization on graphs

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 hybrid attention (HYA) (ablation)MILPnet · FOLD(20,6) feasibilityMSE: 0.2503 -> 0.0001Improved
add multi-scale attention (MSA) (ablation)MILPnet · FOLD(20,6) feasibilityMSE: 0.2500 -> 0.0001Improved
add multi-scale attention (MSA) (ablation)MILPnet · FOLD(100,20) feasibilityErrorN: 4995 -> 6Improved
max window n/2 instead of n/4 (ablation)MILPnet · FOLD(50,30) feasibilityMSE: 0.0841 -> 0.0477Improved
max window n/4 vs n/2 (ablation)MILPnet · FOLD(20,16)MSE: 0.0005 -> 0.0026Mixed
increase attention blocks from 1 to 2 (ablation)MILPnet · FOLD(20,16) feasibilityMSE: 0.0006 -> 0.0001Improved
increase attention blocks from 2 to 3 (ablation)MILPnet · FOLD(20,16) feasibilityMSE: 0.0001 -> 0.0004No clear effect
randomly permute constraint order (ablation)MILPnet · FOLD(50,20) feasibilityMSE: 0.0005 -> 0.0006No clear effect
sequence model instead of GCNGCN · FOLD(50,30) feasibilityMSE: 0.3556 -> 0.0023Improved
sequence model instead of graph modelsSAGE · FOLD(50,20) optimal solutionMSE: 0.1000 -> 0.1158Hurt
sequence model instead of GCNGCN · FOLD(20,6) optimal solutionMSE: 0.0751 -> 0.0473Improved
random feature augmentationGCN · FOLD(50,30) feasibilityMSE: 0.3556 -> 0.5223Hurt

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