AI Paper Atlas

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

DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization

Haoran Ye, Jiarui Wang, Zhiguang Cao, Helan Liang, Yong Li

NeurIPS 2023 · Learning theory and algorithms › Combinatorial and search optimization · approach: Unsupervised neural combinatorial optimization · 23 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 neural-guided perturbation instead of vanilla LS with more iterations (ablation)DeepACO · TSP500tour length: 16.90 -> 16.86Improved
use neural-guided instead of random perturbation (ablation)DeepACO · TSP1000tour length: 23.90 -> 23.85Improved
train with LS term (W=9) instead of W=0 (ablation)DeepACO · TSP500tour length: 17.05 -> 16.86Improved
train with LS term (W=9) instead of W=0 (ablation)DeepACO · TSP1000tour length: 24.23 -> 23.85Improved
replace expert heuristic measures with learned ones (no NLS)Ant System/EAS/MMAS · eight COPsbest-so-far objectiveImproved
apply DeepACO NLS vs plain ACOACO · TSP500gap to LKH-3 (%): 6.16 -> 1.84Improved
add multihead decoder, top-k entropy loss, or imitation loss (ablation)DeepACO · TSP20/50/100best-so-far objectiveImproved
use ACO evolution with pheromone update instead of pure sampling (ablation)DeepACO · routingsolution qualityImproved

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