Generative Adversarial Training for Neural Combinatorial Optimization Models

Liang Xin, Wen Song, Zhiguang Cao, Jie Zhang

Keywords: Vehicle Routing Problems, Combinatorial Optimization, Deep Reinforcement Learning

TL;DR: We propose a general framework to improve the generalization ability of deep learning models for Combinatorial Optimization Problems.

Abstract: Recent studies show that deep neural networks can be trained to learn good heuristics for various Combinatorial Optimization Problems (COPs). However, it remains a great challenge for the trained deep optimization models to generalize to distributions different from the training one. To address this issue, we propose a general framework, Generative Adversarial Neural Combinatorial Optimization (GANCO) which is equipped with another deep model to generate training instances for the optimization model, so as to improve its generalization ability. The two models are trained alternatively in an adversarial way, where the generation model is trained by reinforcement learning to find instance distributions hard for the optimization model. We apply the GANCO framework to two recent deep combinatorial optimization models, i.e., AM and POMO. Extensive experiments on various COPs such as Traveling Salesman Problem, Capacitated Vehicle Routing Problem, and 0-1 Knapsack Problem show that GANCO can significantly improve the generalization ability of optimization models on various instance distributions.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)