用相对位置编码增强Transformer路由，提升复杂路径规划效果
Enhancing Transformer-based Routing by Encoding Distance via Relative Positional Encoding
- 在注意力机制中加入相对位置编码，显式建模节点间空间关系
- 100节点以内实例上，奖励收集量和最优差距均优于基础Transformer
- 适合研究组合优化、图神经网络与智能路径规划的读者
本文探索将相对位置编码（RPE）作为附加偏置引入Transformer架构，以解决团队定向问题。通过在表示路由问题的图中嵌入节点间的成对空间关系，Transformer编码器能够计算出更具空间感知能力的图嵌入，从而帮助解码器更准确地估计路径。实验涉及最多100个节点的实例，结果表明该方法在收集奖励和最优性差距方面持续优于其他先进工作所采用的原始Transformer架构。这些发现表明，显式的关联建模显著提升了复杂组合优化任务的可扩展性和泛化能力。
原文摘要 · Abstract (English)
This paper explores Relative Positional Encoding (RPE) as an additive bias in Transformer architectures to solve the Team Orienteering Problem. By embedding in the attention mechanism pairwise spatial relationships among nodes of the graph that represents the routing problem, the transformer encoder can compute a richer spatial-aware graph embedding that allows the decoder to estimate better routes. Experimental results involving instances up to 100 nodes demonstrate consistent improvements in collected rewards and optimality gaps over vanilla Transformer architectures used by other state-of-the-art works. These findings highlight that explicit relational modeling significantly enhances scalability and generalization for complex combinatorial optimization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。