Prompt Learning for Generalized Vehicle Routing

TL;DR

This paper introduces a prompt learning approach for neural combinatorial optimization that enables fast zero-shot adaptation of pre-trained vehicle routing models across different distributions, outperforming existing methods.

Contribution

It proposes a novel prompt learning method for quick cross-distribution adaptation in vehicle routing problems, reducing the need for fine-tuning or retraining.

Findings

Facilitates fast zero-shot adaptation of routing models.

Outperforms existing generalized models on diverse tasks.

Enables effective cross-distribution generalization.

Abstract

Neural combinatorial optimization (NCO) is a promising learning-based approach to solving various vehicle routing problems without much manual algorithm design. However, the current NCO methods mainly focus on the in-distribution performance, while the real-world problem instances usually come from different distributions. A costly fine-tuning approach or generalized model retraining from scratch could be needed to tackle the out-of-distribution instances. Unlike the existing methods, this work investigates an efficient prompt learning approach in NCO for cross-distribution adaptation. To be concrete, we propose a novel prompt learning method to facilitate fast zero-shot adaptation of a pre-trained model to solve routing problem instances from different distributions. The proposed model learns a set of prompts among various distributions and then selects the best-matched one to prompt a pre-trained attention model for each problem instance. Extensive experiments show that the proposed prompt learning approach facilitates the fast adaptation of pre-trained routing models. It also outperforms existing generalized models on both in-distribution prediction and zero-shot generalization to a diverse set of new tasks. Our code implementation is available online https://github.com/FeiLiu36/PromptVRP.