AI Paper Atlas

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

Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization

Jinbiao Chen, Jiahai Wang, Zizhen Zhang, Zhiguang Cao, Te Ye, Siyuan Chen

NeurIPS 2023 · Learning theory and algorithms › Combinatorial and search optimization · approach: Unsupervised neural combinatorial optimization · 3 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
Use symmetric sampling only (EMNH-S) instead of scaled symmetric sampling (EMNH) (ablation)EMNH · Bi-CVRP n=20HV: 0.4158 -> 0.4299Hurt
Use random weight sampling (EMNH-R) instead of scaled symmetric sampling (ablation)EMNH · Bi-CVRP n=20HV: 0.3774 -> 0.4299Hurt
Random sampling vs symmetric sampling on balanced Bi-TSP-1 (ablation)EMNH · Bi-TSP-1 n=50HV: 0.6339 -> 0.6362Hurt
Add scaled weight sampling to PMOCO (PMOCO-S) (ablation)PMOCO · Bi-CVRP n=100HV: 0.3913 -> 0.4042Improved
Add scaled sampling to PMOCO on Bi-CVRP n=20 (ablation)PMOCO · Bi-CVRP n=20HV: 0.4267 -> 0.4274Improved
Add instance augmentation to EMNHEMNH · Bi-CVRP n=50HV: 0.4098 -> 0.4106Improved
Add instance augmentation to EMNHEMNH · Tri-TSP-1 n=100HV: 0.4866 -> 0.4973Improved
EMNH (meta-learning, accelerated training) instead of MDRLMDRL · Bi-KP n=50HV: 0.3530 -> 0.3561Improved
EMNH vs MDRL on easy balanced instanceMDRL · Bi-TSP-1 n=100HV: 0.6969 -> 0.6969No clear effect
EMNH vs PMOCOPMOCO · Bi-CVRP n=100HV: 0.3913 -> 0.4072Improved
Accelerated training with multi-task architecture reuseMDRL · training timespeed-up: 1/N of MDRL training timeImproved
EMNH-Aug vs WS-LKH on larger MOTSPEMNH-Aug · Bi-TSP-1 n=100HV: 0.7023 vs 0.7090Hurt

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