Equity-Transformer: Solving NP-hard Min-Max Routing Problems as Sequential Generation with Equity Context

TL;DR

Equity-Transformer introduces a sequential generation approach using Transformer models for large-scale min-max routing problems, effectively balancing workloads and significantly reducing runtime and costs in multi-agent routing tasks.

Contribution

The paper presents a novel Transformer-based method with inductive biases for equitable workload distribution in large-scale min-max routing problems, outperforming existing heuristics.

Findings

Achieves 335x runtime reduction in large-scale routing

Reduces cost values by approximately 53% compared to heuristics

Demonstrates effectiveness on min-max mTSP and mPDP tasks

Abstract

Min-max routing problems aim to minimize the maximum tour length among multiple agents by having agents conduct tasks in a cooperative manner. These problems include impactful real-world applications but are known as NP-hard. Existing methods are facing challenges, particularly in large-scale problems that require the coordination of numerous agents to cover thousands of cities. This paper proposes Equity-Transformer to solve large-scale min-max routing problems. First, we employ sequential planning approach to address min-max routing problems, allowing us to harness the powerful sequence generators (e.g., Transformer). Second, we propose key inductive biases that ensure equitable workload distribution among agents. The effectiveness of Equity-Transformer is demonstrated through its superior performance in two representative min-max routing tasks: the min-max multi-agent traveling salesman problem (min-max mTSP) and the min-max multi-agent pick-up and delivery problem (min-max mPDP). Notably, our method achieves significant reductions of runtime, approximately 335 times, and cost values of about 53\% compared to a competitive heuristic (LKH3) in the case of 100 vehicles with 1,000 cities of mTSP. We provide reproducible source code: \url{https://github.com/kaist-silab/equity-transformer}.