Learning to solving vehicle routing problems via local–global feature fusion transformer
Saved in:
| Title: | Learning to solving vehicle routing problems via local–global feature fusion transformer |
|---|---|
| Authors: | Wei Li, Bing Tian Dai, Xueming Yan, Junying Zou, Zhijie Liang, Jingwen Li |
| Source: | Complex & Intelligent Systems, Vol 11, Iss 9, Pp 1-16 (2025) |
| Publisher Information: | Springer, 2025. |
| Publication Year: | 2025 |
| Collection: | LCC:Electronic computers. Computer science LCC:Information technology |
| Subject Terms: | Vehicle routing problems, Deep reinforcement learning, Cross-size and cross-distribution generalization, Learning to optimize, Electronic computers. Computer science, QA75.5-76.95, Information technology, T58.5-58.64 |
| Description: | Abstract Applying Combinatorial optimization problems such as the Vehicle Routing Problems (VRPs) have attracted increasing interest with the emergence of learning-based methods. However, existing neural approaches often struggle to generalize across diverse problem sizes and node distributions, limiting their applicability in real-world scenarios. To overcome these challenges, we propose Local-Global Feature Fusion Transformer (FusionFormer), a novel deep reinforcement learning framework that enhances both solution quality and generalization capability for solving VRPs. Specifically, we introduce a Distance-Assisted Multi-Head Attention (DA-MHA) mechanism that incorporates explicit spatial distance information into the attention computation, thereby preserving spatial consistency and facilitating more robust global representation learning. In addition, we design a Proximity-Guided Attention (PGA) mechanism that dynamically fuses local and global contexts based on node proximity, enabling the model to focus on more relevant decision-making information while reducing sensitivity to distributional shifts. Extensive experiments on both real-world and synthetic benchmarks demonstrate that our FusionFormer consistently outperforms existing neural routing solvers (including those specifically designed for generalization enhancement) and achieves performance competitive with the highly-optimized benchmark LKH3 solver, particularly on unseen problem sizes and node distributions. |
| Document Type: | article |
| File Description: | electronic resource |
| Language: | English |
| ISSN: | 2199-4536 2198-6053 |
| Relation: | https://doaj.org/toc/2199-4536; https://doaj.org/toc/2198-6053 |
| DOI: | 10.1007/s40747-025-02018-0 |
| Access URL: | https://doaj.org/article/94bec5d7b7cd4e4aae0a51994dd1e0f4 |
| Accession Number: | edsdoj.94bec5d7b7cd4e4aae0a51994dd1e0f4 |
| Database: | Directory of Open Access Journals |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | Abstract Applying Combinatorial optimization problems such as the Vehicle Routing Problems (VRPs) have attracted increasing interest with the emergence of learning-based methods. However, existing neural approaches often struggle to generalize across diverse problem sizes and node distributions, limiting their applicability in real-world scenarios. To overcome these challenges, we propose Local-Global Feature Fusion Transformer (FusionFormer), a novel deep reinforcement learning framework that enhances both solution quality and generalization capability for solving VRPs. Specifically, we introduce a Distance-Assisted Multi-Head Attention (DA-MHA) mechanism that incorporates explicit spatial distance information into the attention computation, thereby preserving spatial consistency and facilitating more robust global representation learning. In addition, we design a Proximity-Guided Attention (PGA) mechanism that dynamically fuses local and global contexts based on node proximity, enabling the model to focus on more relevant decision-making information while reducing sensitivity to distributional shifts. Extensive experiments on both real-world and synthetic benchmarks demonstrate that our FusionFormer consistently outperforms existing neural routing solvers (including those specifically designed for generalization enhancement) and achieves performance competitive with the highly-optimized benchmark LKH3 solver, particularly on unseen problem sizes and node distributions. |
|---|---|
| ISSN: | 21994536 21986053 |
| DOI: | 10.1007/s40747-025-02018-0 |