Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2512.07873 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914247071498240 |
|---|---|
| author | Zhang, Ci Li, Huayu Yang, Changdi Xia, Jiangnan Wang, Yanzhi Ma, Xiaolong Lu, Jin Li, Ao Yuan, Geng |
| author_facet | Zhang, Ci Li, Huayu Yang, Changdi Xia, Jiangnan Wang, Yanzhi Ma, Xiaolong Lu, Jin Li, Ao Yuan, Geng |
| contents | Recent studies show that using diffusion models for time series signal reconstruction holds great promise. However, such approaches remain largely unexplored in the domain of medical time series. The unique characteristics of the physiological time series signals, such as multivariate, high temporal variability, highly noisy, and artifact-prone, make deep learning-based approaches still challenging for tasks such as imputation. Hence, we propose a novel Mixture of Experts (MoE)-based noise estimator within a score-based diffusion framework. Specifically, the Receptive Field Adaptive MoE (RFAMoE) module is designed to enable each channel to adaptively select desired receptive fields throughout the diffusion process. Moreover, recent literature has found that when generating a physiological signal, performing multiple inferences and averaging the reconstructed signals can effectively reduce reconstruction errors, but at the cost of significant computational and latency overhead. We design a Fusion MoE module and innovatively leverage the nature of MoE module to generate K noise signals in parallel, fuse them using a routing mechanism, and complete signal reconstruction in a single inference step. This design not only improves performance over previous methods but also eliminates the substantial computational cost and latency associated with multiple inference processes. Extensive results demonstrate that our proposed framework consistently outperforms diffusion-based SOTA works on different tasks and datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_07873 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Advancing time series completion via RFAMoE and MDFF Zhang, Ci Li, Huayu Yang, Changdi Xia, Jiangnan Wang, Yanzhi Ma, Xiaolong Lu, Jin Li, Ao Yuan, Geng Machine Learning Artificial Intelligence Recent studies show that using diffusion models for time series signal reconstruction holds great promise. However, such approaches remain largely unexplored in the domain of medical time series. The unique characteristics of the physiological time series signals, such as multivariate, high temporal variability, highly noisy, and artifact-prone, make deep learning-based approaches still challenging for tasks such as imputation. Hence, we propose a novel Mixture of Experts (MoE)-based noise estimator within a score-based diffusion framework. Specifically, the Receptive Field Adaptive MoE (RFAMoE) module is designed to enable each channel to adaptively select desired receptive fields throughout the diffusion process. Moreover, recent literature has found that when generating a physiological signal, performing multiple inferences and averaging the reconstructed signals can effectively reduce reconstruction errors, but at the cost of significant computational and latency overhead. We design a Fusion MoE module and innovatively leverage the nature of MoE module to generate K noise signals in parallel, fuse them using a routing mechanism, and complete signal reconstruction in a single inference step. This design not only improves performance over previous methods but also eliminates the substantial computational cost and latency associated with multiple inference processes. Extensive results demonstrate that our proposed framework consistently outperforms diffusion-based SOTA works on different tasks and datasets. |
| title | Advancing time series completion via RFAMoE and MDFF |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2512.07873 |