FedAFD：通过对抗融合与蒸馏实现的多模态联邦学习
FedAFD: Multimodal Federated Learning via Adversarial Fusion and Distillation
双层对抗对齐与相似度引导的集成蒸馏，为视觉研究者提供在数据不共享、模态与模型异构条件下融合跨模态表征的可复用机制，可直接迁移到多模态视觉模型的分布式协同训练。
原文依据 a bi-level adversarial alignment strategy to align local and global representations within and across modalities
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多模态联邦学习（MFL）使拥有异构数据模态的客户端能够在不共享原始数据的情况下协同训练模型，提供了一个利用互补跨模态信息的隐私保护框架。然而，现有方法往往忽视客户端的个性化性能，并且在模态/任务差异以及模型异构性方面存在困难。为应对这些挑战，我们提出 FedAFD，一个增强客户端与服务器学习的统一 MFL 框架。在客户端侧，我们引入双层对抗对齐策略，在模态内部与跨模态之间对齐本地表征与全局表征，从而缓解模态与任务差距。我们进一步设计粒度感知融合模块，将全局知识自适应地整合进个性化特征。在服务器侧，为处理模型异构性，我们提出相似度引导的集成蒸馏机制，基于特征相似度在共享公开数据上聚合客户端表征，并将融合后的知识蒸馏进全局模型。在 IID 与非 IID 设置下进行的大量实验表明，FedAFD 在客户端与服务器两侧均取得了更优的性能与效率。
英文原文摘要 1243 字符
Multimodal Federated Learning (MFL) enables clients with heterogeneous data modalities to collaboratively train models without sharing raw data, offering a privacy-preserving framework that leverages complementary cross-modal information. However, existing methods often overlook personalized client performance and struggle with modality/task discrepancies, as well as model heterogeneity. To address these challenges, we propose FedAFD, a unified MFL framework that enhances client and server learning. On the client side, we introduce a bi-level adversarial alignment strategy to align local and global representations within and across modalities, mitigating modality and task gaps. We further design a granularity-aware fusion module to integrate global knowledge into the personalized features adaptively. On the server side, to handle model heterogeneity, we propose a similarity-guided ensemble distillation mechanism that aggregates client representations on shared public data based on feature similarity and distills the fused knowledge into the global model. Extensive experiments conducted under both IID and non-IID settings demonstrate that FedAFD achieves superior performance and efficiency for both the client and the server.