Learning to Solve the Quadratic Assignment Problem with Warm-Started MCMC Finetuning

TL;DR

This paper introduces PLMA, a novel permutation learning framework with warm-started MCMC finetuning and an additive energy-based model, significantly improving QAP solving performance across diverse benchmarks.

Contribution

The paper proposes a new permutation learning approach with an efficient MCMC finetuning method and a scalable attention-based energy model for solving the quadratic assignment problem.

Findings

Achieves near-zero average optimality gap on QAPLIB.

Outperforms state-of-the-art baselines on various benchmarks.

Demonstrates robustness on difficult Taixxeyy instances.

Abstract

The quadratic assignment problem (QAP) is a fundamental NP-hard task that poses significant challenges for both traditional heuristics and modern learning-based solvers. Existing QAP solvers still struggle to achieve consistently competitive performance across structurally diverse real-world instances. To bridge this performance gap, we propose PLMA, an innovative permutation learning framework. PLMA features an efficient warm-started MCMC finetuning procedure to enhance deployment-time performance, leveraging short Markov chains to anchor the adaptation to the promising regions previously explored. For rapid exploration via MCMC over the permutation space, we design an additive energy-based model (EBM) that enables an $O(1)$-time 2-swap Metropolis-Hastings sampling step. Moreover, the neural network used to parameterize the EBM incorporates a scalable and flexible cross-graph attention mechanism to model interactions between facilities and locations in the QAP. Extensive experiments demonstrate that PLMA consistently outperforms state-of-the-art baselines across various benchmarks. In particular, PLMA achieves a near-zero average optimality gap on QAPLIB, exhibits remarkably superior robustness on the notoriously difficult Taixxeyy instances, and also serves as an effective QAP solver in bandwidth minimization.