Neural Bee Colony Optimization: A Case Study in Public Transit Network Design

TL;DR

This paper presents a hybrid neural network and bee colony optimization approach for transit network design, achieving significant improvements over standalone methods on real-world instances.

Contribution

It introduces a novel hybrid algorithm combining neural policies with BCO for transit network design, demonstrating superior performance over existing methods.

Findings

Hybrid algorithm outperforms neural policy alone by up to 20%.

Hybrid algorithm outperforms original BCO by up to 53%.

Ablation studies show the impact of each component.

Abstract

In this work we explore the combination of metaheuristics and learned neural network solvers for combinatorial optimization. We do this in the context of the transit network design problem, a uniquely challenging combinatorial optimization problem with real-world importance. We train a neural network policy to perform single-shot planning of individual transit routes, and then incorporate it as one of several sub-heuristics in a modified Bee Colony Optimization (BCO) metaheuristic algorithm. Our experimental results demonstrate that this hybrid algorithm outperforms the learned policy alone by up to 20% and the original BCO algorithm by up to 53% on realistic problem instances. We perform a set of ablations to study the impact of each component of the modified algorithm.