arXiv cs.AI· Kaiyun Wei, Yue Xu, Wenying Duan, Zichen Xu, Shuai Ma, Xiaoxi He·· 1 天前AI 评分24
TopoST：面向城市时空基础模型的拓扑条件节点特化方法
TopoST: Topology-Conditioned Node Specialization for Urban Spatio-Temporal Foundation Models
AI 导读
TopoST 通过共享的拓扑到参数映射实现可迁移的节点特化，为未见节点直接生成时空依赖参数，无需目标专用嵌入或模型更新。该方法基于 20+ 个城市数据集的分析，发现跨数据集重复出现的局部图结构与局部子图内的显著节点异质性。实验显示 TopoST 在未见城市和任务上实现零样本泛化，代码已开源。
正文 · 原文
Abstract:Urban spatio-temporal foundation models must share knowledge across diverse urban scenarios while accommodating heterogeneous node dynamics. Our analysis of 20+ datasets spanning diverse urban scenarios reveals recurring local graph structures across datasets alongside substantial node heterogeneity within local subgraphs. Motivated by these observations, we propose TopoST, which combines shared learning over local subgraphs with topology-conditioned node specialization. The key insight is to make node specialization itself transferable through a shared topology-to-parameter mapping. This mapping uses identity-independent topological representations to generate node-specific temporal and spatial dependency parameters, enabling direct specialization for unseen nodes without target-specific embeddings or model updates. Extensive experiments demonstrate that TopoST achieves remarkable zero-shot generalization across unseen cities and tasks, highlighting topology-conditioned node specialization as an effective mechanism for transferable urban spatio-temporal foundation models. Code is available at this https URL.
| Subjects: | Social and Information Networks (cs.SI); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.15440 [cs.SI] |
| (or arXiv:2611.15440v1 [cs.SI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.15440 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kaiyun Wei [view email]
[v1]
Wed, 11 Nov 2026 13:14:06 UTC (280 KB)
来源：arXiv cs.AI · arxiv.org