EUVIMEDEUVIMED entdecken
Crossref

Spatial-Temporal Feedback Diffusion Guidance for Controlled Traffic Imputation

Xiaowei Mao, Huihu Ding, Yan Lin, Tingrui Wu, Shengnan Guo, Dazhuo Qiu, Feiling Fang, Jilin Hu, Huaiyu Wan

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (18) · 15528-15536

DOI: 10.1609/aaai.v40i18.38581 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xiaowei Mao und 8 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Imputing missing values in spatial-temporal traffic data is essential for intelligent transportation systems. Among advanced imputation methods, score-based diffusion models have demonstrated competitive performance. These models generate data by reversing a noising process, using observed values as conditional guidance. However, existing diffusion models typically apply a uniform guidance scale across both spatial and temporal dimensions, which is inadequate for nodes with high missing data rates. Sparse observations provide insufficient conditional guidance, causing the generative process to drift toward the learned prior distribution rather than closely following the conditional observations, resulting in suboptimal imputation performance. To address this, we propose FENCE, a spatial-temporal feedback diffusion guidance method designed to adaptively control guidance scales during imputation. First, FENCE introduces a dynamic feedback mechanism that adjusts the guidance scale based on the posterior likelihood approximations. The guidance scale is increased when generated values diverge from observations and reduced when alignment improves, preventing overcorrection. Second, because alignment to observations varies across nodes and denoising steps, a global guidance scale for all nodes is suboptimal. FENCE computes guidance scales at the cluster level by grouping nodes based on their attention scores, leveraging spatial-temporal correlations to provide more accurate guidance. Experimental results on real-world traffic datasets show that FENCE significantly enhances imputation accuracy.

Zitieren

APA

Mao, X., Ding, H., Lin, Y., Wu, T., Guo, S., Qiu, D., Fang, F., Hu, J., & Wan, H. (2026). Spatial-Temporal Feedback Diffusion Guidance for Controlled Traffic Imputation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(18), 15528-15536. https://doi.org/10.1609/aaai.v40i18.38581

Vancouver

Mao X, Ding H, Lin Y, Wu T, Guo S, Qiu D, et al. Spatial-Temporal Feedback Diffusion Guidance for Controlled Traffic Imputation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(18):15528-15536. doi:10.1609/aaai.v40i18.38581

BibTeX
@article{Mao2026,
  author = {Mao, Xiaowei and Ding, Huihu and Lin, Yan and Wu, Tingrui and Guo, Shengnan and Qiu, Dazhuo and Fang, Feiling and Hu, Jilin and Wan, Huaiyu},
  title = {Spatial-Temporal Feedback Diffusion Guidance for Controlled Traffic Imputation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {18},
  pages = {15528--15536},
  doi = {10.1609/aaai.v40i18.38581}
}
Kostenlos starten →