Saved in:
Bibliographic Details
Main Authors: Liao, Zijun, Chen, Jinbiao, Wang, Debing, Zhang, Zizhen, Wang, Jiahai
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.07580
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918042570588160
author Liao, Zijun
Chen, Jinbiao
Wang, Debing
Zhang, Zizhen
Wang, Jiahai
author_facet Liao, Zijun
Chen, Jinbiao
Wang, Debing
Zhang, Zizhen
Wang, Jiahai
contents Neural Combinatorial Optimization (NCO) has emerged as a promising approach for NP-hard problems. However, prevailing RL-based methods suffer from low sample efficiency due to sparse rewards and underused solutions. We propose Best-anchored and Objective-guided Preference Optimization (BOPO), a training paradigm that leverages solution preferences via objective values. It introduces: (1) a best-anchored preference pair construction for better explore and exploit solutions, and (2) an objective-guided pairwise loss function that adaptively scales gradients via objective differences, removing reliance on reward models or reference policies. Experiments on Job-shop Scheduling Problem (JSP), Traveling Salesman Problem (TSP), and Flexible Job-shop Scheduling Problem (FJSP) show BOPO outperforms state-of-the-art neural methods, reducing optimality gaps impressively with efficient inference. BOPO is architecture-agnostic, enabling seamless integration with existing NCO models, and establishes preference optimization as a principled framework for combinatorial optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2503_07580
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BOPO: Neural Combinatorial Optimization via Best-anchored and Objective-guided Preference Optimization
Liao, Zijun
Chen, Jinbiao
Wang, Debing
Zhang, Zizhen
Wang, Jiahai
Machine Learning
Neural Combinatorial Optimization (NCO) has emerged as a promising approach for NP-hard problems. However, prevailing RL-based methods suffer from low sample efficiency due to sparse rewards and underused solutions. We propose Best-anchored and Objective-guided Preference Optimization (BOPO), a training paradigm that leverages solution preferences via objective values. It introduces: (1) a best-anchored preference pair construction for better explore and exploit solutions, and (2) an objective-guided pairwise loss function that adaptively scales gradients via objective differences, removing reliance on reward models or reference policies. Experiments on Job-shop Scheduling Problem (JSP), Traveling Salesman Problem (TSP), and Flexible Job-shop Scheduling Problem (FJSP) show BOPO outperforms state-of-the-art neural methods, reducing optimality gaps impressively with efficient inference. BOPO is architecture-agnostic, enabling seamless integration with existing NCO models, and establishes preference optimization as a principled framework for combinatorial optimization.
title BOPO: Neural Combinatorial Optimization via Best-anchored and Objective-guided Preference Optimization
topic Machine Learning
url https://arxiv.org/abs/2503.07580