AI Paper Atlas

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

MEGO: Learning Mixture-of-Experts for General-Purpose Binary Optimization

Shengcai Liu, Zi Wang, Yew-Soon Ong, Yao Xin, Ke Tang

TPAMI 2026 · Learning theory and algorithms › Combinatorial and search optimization · approach: Multi-objective optimization · 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 decoder fine-tuning and source-target mapping (ablation)MEGO · 72 test instances (6 classes)Wilcoxon W-D-L vs no mapping: 67 W, 4 D, 1 LImproved
sample in source space instead of searching the latent space (ablation)MEGO · 72 test instances (6 classes)Wilcoxon W-D-L vs latent-space search: 53 W, 16 D, 3 LImproved
use all-one padding instead of zero padding (ablation)MEGO · Dim=20 instances (18)Wilcoxon W-D-L: 2-15-1No clear effect
use random padding instead of zero padding (ablation)MEGO · Dim=20 instances (18)Wilcoxon W-D-L: 2-14-2No clear effect
correlation-based routing instead of random selection of same number of experts (SAMPLE) (ablation)MEGO · 72 test instancesWilcoxon W-D-L: 19-45-8Improved
activate multiple relevant experts instead of one random expert (MEAN) (ablation)MEGO · 72 test instancesWilcoxon W-D-L: 71-0-1Improved
compare MEGO routing against hindsight best single expert (MAX) (ablation)MEGO · 72 test instancesWilcoxon W-D-L: 9-15-48Hurt
use MEGO outputs to warm-start GA, HC and BOGA/HC/BO · CA classW-D-L MEGO+X vs X: 4-8-0, 5-7-0, 6-6-0Improved
use MEGO outputs to warm-start GA, HC and BOGA/HC/BO · CIM classW-D-L MEGO+X vs X: 9-3-0, 11-1-0, 12-0-0Improved
use MEGO outputs to warm-start GA, HC and BOGA/HC/BO · AS classW-D-L MEGO+X vs X: 9-3-0, 12-0-0, 11-1-0Improved
warm-start BO with MEGO against specialized SMARTESTBO · CA, 12 instances, #FEs=800W-D-L MEGO+BO vs SMARTEST: 5-7-0Improved
warm-start BO with MEGOBO · CA, 12 instances, #FEs=800W-D-L MEGO+BO vs BO: 6-6-0Improved

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