Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

12-2022

Abstract

Recent neural methods for vehicle routing problems always train and test the deep models on the same instance distribution (i.e., uniform). To tackle the consequent cross-distribution generalization concerns, we bring the knowledge distillation to this field and propose an Adaptive Multi-Distribution Knowledge Distillation (AMDKD) scheme for learning more generalizable deep models. Particularly, our AMDKD leverages various knowledge from multiple teachers trained on exemplar distributions to yield a light-weight yet generalist student model. Meanwhile, we equip AMDKD with an adaptive strategy that allows the student to concentrate on difficult distributions, so as to absorb hard-to-master knowledge more effectively. Extensive experimental results show that, compared with the baseline neural methods, our AMDKD is able to achieve competitive results on both unseen in-distribution and out-of-distribution instances, which are either randomly synthesized or adopted from benchmark datasets (i.e., TSPLIB and CVRPLIB). Notably, our AMDKD is generic, and consumes less computational resources for inference.

Keywords

Learning systems, Vehicle routing

Discipline

Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

Proceedings of the 36th Conference on Neural Information Processing System, New Orleans, USA, 2022 Nov 28-Dec 09

Volume

35

ISBN

9781713871088

Identifier

10.48550/arXiv.2210.07686

Publisher

Neural information processing systems foundation

City or Country

California

Copyright Owner and License

Authors

Additional URL

http://doi.org/10.48550/arXiv.2210.07686

Download

Share

COinS