Authors
- Hao Du Jilin University, China
- Wenbin Liu Jilin University, China
- Ziyu Sun Jilin University, China
- Haoyang Su Jilin University, China
- En Wang Jilin University, China
- Yuanbo Xu Jilin University, China
DOI:
https://doi.org/10.1609/aaai.v40i1.36985Abstract
Sparse Urban CrowdSensing (Sparse UCS) is a practical paradigm for completing full sensing maps from limited observations. However, existing methods typically rely on a time-discrete assumption, where data is considered static within fixed intervals. This simplification introduces significant errors as real-world data changes continuously. To address this, we propose a framework for time-continuous data completion. Our approach, Time-Aware Mamba-based Deep Matrix Factorization (TIME-DMF), leverages the Mamba architecture as a powerful temporal encoder. Crucially, we enhance Mamba with a novel time-aware mechanism that explicitly incorporates the actual, often irregular, physical time intervals between observations into its state transitions. This allows our model to accurately capture true temporal dynamics and generate high-fidelity data for any queried moment in time through a query-generate mechanism. Extensive experiments on five diverse sensing tasks demonstrate that TIME-DMF significantly outperforms state-of-the-art methods, validating the superiority of the time-continuous paradigm for Sparse UCS.
How to Cite
Du, H., Liu, W., Sun, Z., Su, H., Wang, E., & Xu, Y. (2026). Toward Time-Continuous Data Inference in Sparse Urban CrowdSensing. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 246–254. https://doi.org/10.1609/aaai.v40i1.36985
Issue
Section
AAAI Technical Track on Application Domains I