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

2025-06-22

AI Summary

To address the dual challenges of poor cross-domain generalization and high computational complexity in urban spatiotemporal forecasting, this paper proposes an efficient domain-adaptive model built upon the Mamba architecture. Methodologically, we design a shared–domain-specific latent subspace decomposition mechanism, integrate three plug-and-play domain adapters, and employ latent state alignment to mitigate negative transfer and enhance cross-domain consistency. Leveraging Mamba’s linear-complexity state-space modeling, our approach enables lightweight, scalable multi-domain joint learning. Experiments on multiple city-level traffic flow prediction benchmarks demonstrate that our model significantly outperforms Transformer-based baselines. It exhibits strong zero-shot transfer capability, enabling rapid deployment to data-scarce or previously unseen cities. The framework thus advances both the theoretical foundation and practical applicability of domain-adaptive spatiotemporal forecasting.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Application Domains: Transportation

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Training urban spatio-temporal foundation models that generalize well across diverse regions and cities 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 spatio-temporal prediction. However, directly applying Mamba as a spatio-temporal backbone leads to negative transfer and severe performance degradation. This is primarily due to 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 cross-domain commonalities. Extensive experiments demonstrate the generalization and efficiency of Damba-ST. It achieves state-of-the-art performance on prediction tasks and demonstrates strong zero-shot generalization, enabling seamless deployment in new urban environments without extensive retraining or fine-tuning.

Problem

• Efficient urban spatio-temporal prediction across diverse regions
• Overcoming quadratic complexity and memory overhead in Transformer models
• Addressing spatio-temporal heterogeneity and cross-domain generalization challenges

Innovation

• Domain-adaptive state space model
• Three distinct Domain Adapters
• Linear complexity Mamba enhancement