VAGPO: Vision-augmented Asymmetric Group Preference Optimization for Graph Routing Problems
This addresses efficiency and scalability issues in data-driven optimization for web-related networks, offering incremental improvements over existing methods.
The paper tackles graph routing problems like TSP and CVRP by proposing VAGPO, which uses vision-augmented encoding and asymmetric group preference optimization to improve training efficiency and generalization, achieving competitive solution quality and scaling to 1000 nodes without re-training.
Graph routing problems play a vital role in web-related networks, where finding optimal paths across graphs is essential for efficient data transmission and content delivery. Classic routing formulations such as the Traveling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP) represent fundamental graph optimization challenges. Recent data-driven optimization methods have made significant progress, yet they often face limitations in training efficiency and generalization to large-scale instances. In this paper, we propose a novel Vision-augmented Asymmetric Group Preference Optimization (VAGPO) approach. By leveraging ResNet-based visual encoding and Transformer-based sequential modeling, VAGPO captures both spatial structure and temporal dependencies. Furthermore, we introduce an asymmetric group preference optimization strategy that significantly accelerates convergence compared to commonly used policy gradient methods. Experimental results on generated TSP and CVRP instances, as well as real-world datasets, demonstrate that the proposed VAGPO approach achieves highly competitive solution quality. Additionally, VAGPO exhibits strong generalization to larger instances (up to 1000 nodes) without re-training, highlighting its effectiveness in both learning efficiency and scalability.