通过解耦属性表示，实现车辆路径问题的跨问题泛化。
ARC: Leveraging Compositional Representations for Cross-Problem Learning on VRPs
- 将属性分解为不变语义与上下文交互两部分，提升模型泛化能力。
- 在零样本、少样本及真实场景下均达到最优性能。
- 适合需要快速适应新约束条件的物流优化场景。
具有多样化现实属性的车辆路径问题（VRPs）推动了跨问题学习方法的发展，以实现对不同问题变体的高效泛化。本文提出ARC（基于组合学习的属性表示），一种跨问题学习框架，通过将属性表示分解为两个互补成分：用于不变属性语义的内在属性嵌入（IAE）和用于属性组合效应的上下文交互嵌入（CIE）。这种解耦通过在嵌入空间中强制类比一致性来实现，确保添加属性（如长度约束）的语义变换在不同问题情境中保持一致。这使得模型能够复用已训练变体中的不变语义，并构建未见组合的表示。ARC在分布内、零样本泛化、少样本适应及真实世界基准测试中均达到当前最优性能。
原文摘要 · Abstract (English)
Vehicle Routing Problems (VRPs) with diverse real-world attributes have driven recent interest in cross-problem learning approaches that efficiently generalize across problem variants. We propose ARC (Attribute Representation via Compositional Learning), a cross-problem learning framework that learns disentangled attribute representations by decomposing them into two complementary components: an Intrinsic Attribute Embedding (IAE) for invariant attribute semantics and a Contextual Interaction Embedding (CIE) for attribute-combination effects. This disentanglement is achieved by enforcing analogical consistency in the embedding space to ensure the semantic transformation of adding an attribute (e.g., a length constraint) remains invariant across different problem contexts. This enables our model to reuse invariant semantics across trained variants and construct representations for unseen combinations. ARC achieves state-of-the-art performance across in-distribution, zero-shot generalization, few-shot adaptation, and real-world benchmarks.
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。