跳到主要导航 跳到搜索 跳到主要内容

Damba-ST: Domain-Adaptive Mamba for Efficient Urban Spatio-Temporal Prediction

  • Rui An
  • , Yifeng Zhang
  • , Ziran Liang
  • , Wenqi Fan
  • , Yuxuan Liang
  • , Xuequn Shang
  • , Qing Li
  • Northwestern Polytechnical University Xian
  • Hong Kong Polytechnic University
  • Hong Kong University of Science and Technology

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Training urban spatio-temporal foundation models that generalize well across diverse regions and cities (i.e., crossdomain scenarios) is critical for deploying urban services in unseen or data-scarce regions. Recent studies have typically focused on fusing cross-domain spatio-temporal data to train unified Transformer-based models. However, these models suffer from quadratic computational complexity and high memory overhead, limiting their scalability and practical deployment. Inspired by the efficiency of Mamba, a state-space model with linear time complexity, we explore its potential for efficient urban spatiotemporal prediction. However, directly applying Mamba as a spatio-temporal backbone leads to negative transfer and severe performance degradation in unseen regions. This is primarily due to inherent spatio-temporal heterogeneity and the recursive mechanism of Mamba's hidden state updates, which limit cross-domain generalization. To overcome these challenges, we propose Damba-ST, a novel domain-adaptive Mamba-based model for efficient urban spatio-temporal prediction. Damba-ST retains Mamba's linear complexity advantage while significantly enhancing its adaptability to heterogeneous domains. Specifically, we introduce two core innovations: (1) a Domain-Adaptive State Space Model that partitions the latent representation space into a shared subspace for learning cross-domain commonalities and independent, domain-specific subspaces for capturing intra-domain discriminative features; (2) three distinct Domain Adapters, which serve as domain-aware proxies to bridge disparate domain distributions and facilitate the alignment of crossdomain commonalities. Extensive experiments demonstrate the generalization and efficiency of Damba-ST. It achieves state-ofthe-art performance on prediction tasks and demonstrates strong zero-shot generalization, enabling seamless deployment in new urban environments without extensive retraining or fine-tuning. The code is available at https://github.com/RuiAN77/Damba-ST.

源语言英语
主期刊名Proceedings - 2026 IEEE 42nd International Conference on Data Engineering, ICDE 2026
编辑Khuzaima Daudjee, Qiong Luo, Alkis Simitsis
出版商Institute of Electrical and Electronics Engineers Inc.
页1349-1362
页数14
ISBN(电子版)9798331583651
DOI
出版状态已出版 - 2026
活动42nd International Conference on Data Engineering, ICDE 2026 - Montreal, 加拿大
期限: 4 5月 2026 → …

丛书

姓名Proceedings - 2026 IEEE 42nd International Conference on Data Engineering, ICDE 2026

会议

会议42nd International Conference on Data Engineering, ICDE 2026
国家/地区加拿大
市Montreal
时期4/05/26 → …

学术指纹

探究 'Damba-ST: Domain-Adaptive Mamba for Efficient Urban Spatio-Temporal Prediction' 的科研主题。它们共同构成独一无二的学术指纹。

引用此