Enhancing Cross-Problem Vehicle Routing via Federated Learning

2026-04-12

AI Summary

This work addresses the performance degradation and limited generalization in cross-problem vehicle routing optimization (VRP) caused by diverse and complex constraints. To tackle this challenge, we propose MPSF-FL, a federated learning framework based on “multi-problem pretraining followed by single-problem fine-tuning.” MPSF-FL introduces federated learning to cross-problem VRP for the first time, enabling a global model to share generalizable path optimization knowledge while allowing local models to efficiently adapt to downstream tasks with heterogeneous constraints. By integrating neural combinatorial optimization with multi-task pretraining and single-task fine-tuning strategies, MPSF-FL achieves significant performance improvements across multiple VRP variants and demonstrates superior generalization on unseen problem instances.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Vehicle routing problems (VRPs) constitute a core optimization challenge in modern logistics and supply chain management. The recent neural combinatorial optimization (NCO) has demonstrated superior efficiency over some traditional algorithms. While serving as a primary NCO approach for solving general VRPs, current cross-problem learning paradigms are still subject to performance degradation and generalizability decay, when transferring from simple VRP variants to those involving different and complex constraints. To strengthen the paradigms, this paper offers an innovative "Multi-problem Pre-train, then Single-problem Fine-tune" framework with Federated Learning (MPSF-FL). This framework exploits the common knowledge of a federated global model to foster efficient cross-problem knowledge sharing and transfer among local models for single-problem fine-tuning. In this way, local models effectively retain common VRP knowledge from up-to-date global model, while being efficiently adapted to downstream VRPs with heterogeneous complex constraints. Experimental results demonstrate that our framework not only enhances the performance in diverse VRPs, but also improves the generalizability in unseen problems.

Problem

• Vehicle Routing Problem
• Cross-problem Learning
• Generalizability
• Neural Combinatorial Optimization
• Complex Constraints

Innovation

• Federated Learning
• Neural Combinatorial Optimization
• Cross-problem Transfer
• Vehicle Routing Problem
• Multi-task Pre-training