Adversarial Instance Generation and Robust Training for Neural Combinatorial Optimization with Multiple Objectives

February 09, 2026

Reading time: 1 minute

...

📝 Original Info

Title: Adversarial Instance Generation and Robust Training for Neural Combinatorial Optimization with Multiple Objectives
ArXiv ID: 2601.01665
Date: 2026-01-04
Authors: Wei Liu, Yaoxin Wu, Yingqian Zhang, Thomas Bäck, Yingjie Fan

📝 Abstract

Deep reinforcement learning (DRL) has shown great promise in addressing multiobjective combinatorial optimization problems (MOCOPs). Nevertheless, the robustness of these learning-based solvers has remained insufficiently explored, especially across diverse and complex problem distributions. In this paper, we propose a unified robustness-oriented framework for preference-conditioned DRL solvers for MO-COPs. Within this framework, we develop a preference-based adversarial attack to generate hard instances that expose solver weaknesses, and quantify the attack impact by the resulting degradation on Pareto-front quality. We further introduce a defense strategy that integrates hardness-aware preference selection into adversarial training to reduce overfitting to restricted preference regions and improve out-of-distribution performance. The experimental results on multi-objective traveling salesman problem (MOTSP), multi-objective capacitated vehicle routing problem (MOCVRP), and multiobjective knapsack problem (MOKP) verify that our attack method successfully learns hard instances for different solvers. Furthermore, our defense method significantly strengthens the robustness and gen...

📄 Full Content

...(본문 내용이 길어 생략되었습니다. 사이트에서 전문을 확인해 주세요.)

Adversarial Instance Generation and Robust Training for Neural Combinatorial Optimization with Multiple Objectives

📝 Original Info

📝 Abstract

📄 Full Content

Table of Contents

Table of Contents

📝 Original Info

📝 Abstract

📄 Full Content

Start searching

No results found