Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2603.13291 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918387698892800 |
|---|---|
| author | Zhu, Xianxun Sun, Zezhong Rida, Imad Cambria, Erik Su, Junqi Wang, Rui Chen, Hui |
| author_facet | Zhu, Xianxun Sun, Zezhong Rida, Imad Cambria, Erik Su, Junqi Wang, Rui Chen, Hui |
| contents | Multimodal sentiment analysis in federated learning environments faces significant challenges due to missing modalities, heterogeneous data distributions, and unreliable client updates. Existing federated approaches often struggle to maintain robust performance under these practical conditions. In this paper, we propose FedUAF, a unified multimodal federated learning framework that addresses these challenges through uncertainty-aware fusion and reliability-guided aggregation. FedUAF explicitly models modality-level uncertainty during local training and leverages client reliability to guide global aggregation, enabling effective learning under incomplete and noisy multimodal data. Extensive experiments on CMU-MOSI and CMU-MOSEI demonstrate that FedUAF consistently outperforms state-of-the-art federated baselines across various missing-modality patterns and Non-IID settings. Moreover, FedUAF exhibits superior robustness against noisy clients, highlighting its potential for real-world multimodal federated applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13291 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FedUAF: Uncertainty-Aware Fusion with Reliability-Guided Aggregation for Multimodal Federated Sentiment Analysis Zhu, Xianxun Sun, Zezhong Rida, Imad Cambria, Erik Su, Junqi Wang, Rui Chen, Hui Machine Learning Artificial Intelligence Multimodal sentiment analysis in federated learning environments faces significant challenges due to missing modalities, heterogeneous data distributions, and unreliable client updates. Existing federated approaches often struggle to maintain robust performance under these practical conditions. In this paper, we propose FedUAF, a unified multimodal federated learning framework that addresses these challenges through uncertainty-aware fusion and reliability-guided aggregation. FedUAF explicitly models modality-level uncertainty during local training and leverages client reliability to guide global aggregation, enabling effective learning under incomplete and noisy multimodal data. Extensive experiments on CMU-MOSI and CMU-MOSEI demonstrate that FedUAF consistently outperforms state-of-the-art federated baselines across various missing-modality patterns and Non-IID settings. Moreover, FedUAF exhibits superior robustness against noisy clients, highlighting its potential for real-world multimodal federated applications. |
| title | FedUAF: Uncertainty-Aware Fusion with Reliability-Guided Aggregation for Multimodal Federated Sentiment Analysis |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2603.13291 |