Self-Improved Learning for Scalable Neural Combinatorial Optimization

TL;DR

This paper introduces a Self-Improved Learning method for neural combinatorial optimization that enhances scalability to large problem instances like TSP and CVRP with up to 100K nodes, without requiring labeled data.

Contribution

It proposes a novel self-improved mechanism with local reconstruction and a linear attention model to efficiently solve large-scale combinatorial problems.

Findings

Successfully applied to TSP and CVRP with up to 100K nodes

Achieves better solutions through iterative self-improvement

Maintains low computational overhead with linear attention

Abstract

The end-to-end neural combinatorial optimization (NCO) method shows promising performance in solving complex combinatorial optimization problems without the need for expert design. However, existing methods struggle with large-scale problems, hindering their practical applicability. To overcome this limitation, this work proposes a novel Self-Improved Learning (SIL) method for better scalability of neural combinatorial optimization. Specifically, we develop an efficient self-improved mechanism that enables direct model training on large-scale problem instances without any labeled data. Powered by an innovative local reconstruction approach, this method can iteratively generate better solutions by itself as pseudo-labels to guide efficient model training. In addition, we design a linear complexity attention mechanism for the model to efficiently handle large-scale combinatorial problem instances with low computation overhead. Comprehensive experiments on the Travelling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP) with up to 100K nodes in both uniform and real-world distributions demonstrate the superior scalability of our method.