解决联邦学习中多模态数据缺失与噪声问题，提升情感分析鲁棒性。
FedUAF: Uncertainty-Aware Fusion with Reliability-Guided Aggregation for Multimodal Federated Sentiment Analysis
- 通过模态不确定性建模和客户端可靠性评估融合多源信息。
- 在多种数据缺失和非独立同分布场景下，性能优于现有方法。
- 适合真实场景中存在数据不全或异常客户端的多模态联邦学习应用。
联邦学习环境下的多模态情感分析面临模态缺失、数据分布异质性和客户端更新不可靠等挑战。现有联邦方法在这些实际条件下难以保持稳定性能。本文提出 FedUAF，一种统一的多模态联邦学习框架，通过不确定性感知融合与可靠性引导聚合来应对上述问题。该框架在本地训练中显式建模各模态的不确定性，并利用客户端可靠性指导全局聚合，从而在不完整且含噪的多模态数据下实现有效学习。在 CMU-MOSI 与 CMU-MOSEI 数据集上的大量实验表明，无论在何种模态缺失模式或 Non-IID 设置下，FedUAF 均持续优于当前最优联邦基线。此外，该方法对噪声客户端表现出更强鲁棒性，展现出在真实多模态联邦应用中的潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。