AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability

Zijie Geng, Xijun Li, Jie Wang, Xiao Li, Yongdong Zhang, Feng Wu

NeurIPS 2023 · Learning theory and algorithms › Combinatorial and search optimization · approach: Learning branch-and-cut for MILP · 4 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
replace G2MILP decoder networks with random generators (Random) (ablation)G2MILP · MISstructural similarity score: 0.997 vs 0.651Hurt
increase masking ratio from 0.01 to 0.1 (ablation)G2MILP · MISstructural similarity score: 0.997 -> 0.895Hurt
increase masking ratio from 0.01 to 0.1 (ablation)G2MILP · MIKstructural similarity score: 0.991 -> 0.918Hurt
increase masking ratio from 0.01 to 0.1 (ablation)G2MILP · MISGurobi solving time (s): 0.354 -> 0.214Hurt
increase masking ratio from 0.01 to 0.1 (ablation)G2MILP · MIKGurobi solving time (s): 0.169 -> 0.072Hurt
increase masking ratio from 0.01 to 0.1 (ablation)G2MILP · MISaverage branching nodes: 15.03 -> 4.61Hurt
replace Random with G2MILP at eta=0.1 (ablation)Random generator · MISaverage branching nodes: 484.47 -> 4.61Improved
augment training data with G2MILP instances (ablation)GNN value predictor · MIKMSE: 0.0236 -> 0.0073Improved
augment training data with Random instances (ablation)GNN value predictor · MIKMSE: 0.0236 -> 0.0104Improved
augment training data with G2MILP instances (ablation)GNN value predictor · Nurse SchedulingMSE: 679.75 -> 548.70Improved
augment training data with Bowly instances (ablation)GNN value predictor · Nurse SchedulingMSE: 679.75 -> 663.52No clear effect
augment predict-and-search training data with G2MILP instances (ablation)predict-and-search · MISGurobi time: 0.041 -> 0.032Improved

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