Towards Efficient Constraint Handling in Neural Solvers for Routing Problems

TL;DR

This paper introduces Construct-and-Refine (CaR), a novel neural routing solver framework that explicitly learns to handle complex constraints efficiently, outperforming existing methods in feasibility and solution quality.

Contribution

CaR is the first general, efficient constraint-handling framework for neural routing problems using explicit feasibility refinement and shared representations.

Findings

CaR achieves higher feasibility and solution quality.

CaR is more efficient, requiring fewer improvement steps.

CaR outperforms classical and neural state-of-the-art solvers.

Abstract

Neural solvers have achieved impressive progress in addressing simple routing problems, particularly excelling in computational efficiency. However, their advantages under complex constraints remain nascent, for which current constraint-handling schemes via feasibility masking or implicit feasibility awareness can be inefficient or inapplicable for hard constraints. In this paper, we present Construct-and-Refine (CaR), the first general and efficient constraint-handling framework for neural routing solvers based on explicit learning-based feasibility refinement. Unlike prior construction-search hybrids that target reducing optimality gaps through heavy improvements yet still struggle with hard constraints, CaR achieves efficient constraint handling by designing a joint training framework that guides the construction module to generate diverse and high-quality solutions well-suited for a lightweight improvement process, e.g., 10 steps versus 5k steps in prior work. Moreover, CaR presents the first use of construction-improvement-shared representation, enabling potential knowledge sharing across paradigms by unifying the encoder, especially in more complex constrained scenarios. We evaluate CaR on typical hard routing constraints to showcase its broader applicability. Results demonstrate that CaR achieves superior feasibility, solution quality, and efficiency compared to both classical and neural state-of-the-art solvers.