DEG: Diffusion-Enhanced GFlowNet for Solving Vehicle Routing Problems

The paper introduces Diffusion-Enhanced GFlowNet (DEG), a framework that combines Generative Flow Networks with diffusion models to improve vehicle routing problem solutions. DEG uses GFlowNet to generate edge-level signals, perturbs them with diffusion noise, and denoises them to expand flow into high-reward regions, thereby increasing solution diversity. A scalable decoder is added, and experiments on synthetic and real datasets—including up to 10,000-node instances—show DEG outperforms baseline methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• diffusion