将时空模型拆解为通用时间与特定空间两部分，实现高效跨数据集泛化。
Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Models
- 先用掩码序列训练通用时间模型，再用轻量适配器注入空间信息
- 在零样本和少样本场景下性能超越现有模型，线性提升效率
- 适合需要快速部署到新领域的时空预测任务
时空基础模型（STFMs）有望实现跨数据集泛化，但联合预训练成本高，且受限于领域特有的空间模式差异。本文在前期工作基础上提出FactoST-v2，一种可全权重迁移、支持任意长度泛化的因子化框架。该方法将通用时间学习与特定空间适应分离：第一阶段通过随机序列掩码训练极简编码器，捕捉不变的时间动态，实现跨不同预测时长的概率分位数预测；第二阶段采用轻量化适配器，通过元自适应学习和提示机制快速注入空间感知。在多领域综合评估中，FactoST-v2在零样本与少样本场景下显著优于现有基础模型，性能接近领域专用专家模型，同时保持线性计算效率。该因子化范式为构建真正通用的时空基础模型提供了可行、可扩展路径。代码已开源：https://github.com/CityMind-Lab/FactoST。
原文摘要 · Abstract (English)
Spatio-Temporal (ST) Foundation Models (STFMs) promise cross-dataset generalization, yet joint ST pretraining is computationally expensive and grapples with the heterogeneity of domain-specific spatial patterns. Substantially extending our preliminary conference version, we present FactoST-v2, an enhanced factorized framework redesigned for full weight transfer and arbitrary-length generalization. FactoST-v2 decouples universal temporal learning from domain-specific spatial adaptation. The first stage pretrains a minimalist encoder-only backbone using randomized sequence masking to capture invariant temporal dynamics, enabling probabilistic quantile prediction across variable horizons. The second stage employs a streamlined adapter to rapidly inject spatial awareness via meta adaptive learning and prompting. Comprehensive evaluations across diverse domains demonstrate that FactoST-v2 achieves state-of-the-art accuracy with linear efficiency - significantly outperforming existing foundation models in zero-shot and few-shot scenarios while rivaling domain-specific expert baselines. This factorized paradigm offers a practical, scalable path toward truly universal STFMs. Code is available at https://github.com/CityMind-Lab/FactoST.
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。