Cross-Problem Learning for Solving Vehicle Routing Problems

TL;DR

This paper introduces a cross-problem learning approach that pre-trains a Transformer model on the TSP and fine-tunes it for various vehicle routing problem variants, improving efficiency and performance.

Contribution

It proposes a modular neural architecture with pre-training and fine-tuning strategies for different VRP variants, enhancing transferability and efficiency.

Findings

Full fine-tuning outperforms training from scratch.

Adapter-based fine-tuning is parameter-efficient with comparable results.

Method improves cross-distribution application and versatility.

Abstract

Existing neural heuristics often train a deep architecture from scratch for each specific vehicle routing problem (VRP), ignoring the transferable knowledge across different VRP variants. This paper proposes the cross-problem learning to assist heuristics training for different downstream VRP variants. Particularly, we modularize neural architectures for complex VRPs into 1) the backbone Transformer for tackling the travelling salesman problem (TSP), and 2) the additional lightweight modules for processing problem-specific features in complex VRPs. Accordingly, we propose to pre-train the backbone Transformer for TSP, and then apply it in the process of fine-tuning the Transformer models for each target VRP variant. On the one hand, we fully fine-tune the trained backbone Transformer and problem-specific modules simultaneously. On the other hand, we only fine-tune small adapter networks along with the modules, keeping the backbone Transformer still. Extensive experiments on typical VRPs substantiate that 1) the full fine-tuning achieves significantly better performance than the one trained from scratch, and 2) the adapter-based fine-tuning also delivers comparable performance while being notably parameter-efficient. Furthermore, we empirically demonstrate the favorable effect of our method in terms of cross-distribution application and versatility.