标题： 基于客户端自适应焦点调制的可泛化的联邦学习 显示英文标题

标题： Generalizable Federated Learning using Client Adaptive Focal Modulation

摘要： 联邦学习（FL）已被证明在跨分布式客户端的隐私保护协作训练中至关重要。 我们的先前工作，TransFed，引入了一个基于变压器的鲁棒联邦学习框架，该框架利用学习适应的超网络为每个客户端生成个性化的焦点调制层，在非独立同分布和跨领域设置中优于传统方法。 在本扩展版本中，我们提出了AdaptFED，通过结合以下内容来深入研究通用联邦学习中的焦点调制：（1）一种改进的适应策略，整合任务感知的客户端嵌入以进一步个性化调制动态，（2）对适应性能的增强理论边界，以及（3）在更多模态上的广泛实证验证，包括时间序列和多语言数据。 我们还引入了TransFed的一种高效变体，通过低秩超网络条件减少服务器-客户端通信开销，使在资源受限环境中的可扩展部署成为可能。 在八个多样化数据集上的大量实验证实了我们的方法在源自由和跨任务联邦设置中优于最先进的基线。 我们的发现不仅扩展了焦点调制在FL中的能力，也为更适应、可扩展和通用的基于变压器的联邦系统铺平了道路。 代码可在 http://github.com/Tajamul21/TransFed 获取。 显示英文摘要

摘要： Federated learning (FL) has proven essential for privacy-preserving, collaborative training across distributed clients. Our prior work, TransFed, introduced a robust transformer-based FL framework that leverages a learn-to-adapt hypernetwork to generate personalized focal modulation layers per client, outperforming traditional methods in non-IID and cross-domain settings. In this extended version, we propose AdaptFED, where we deepen the investigation of focal modulation in generalizable FL by incorporating: (1) a refined adaptation strategy that integrates task-aware client embeddings to personalize modulation dynamics further, (2) enhanced theoretical bounds on adaptation performance, and (3) broader empirical validation across additional modalities, including time-series and multilingual data. We also introduce an efficient variant of TransFed that reduces server-client communication overhead via low-rank hypernetwork conditioning, enabling scalable deployment in resource-constrained environments. Extensive experiments on eight diverse datasets reaffirm the superiority of our method over state-of-the-art baselines, particularly in source-free and cross-task federated setups. Our findings not only extend the capabilities of focal modulation in FL but also pave the way for more adaptive, scalable, and generalizable transformer-based federated systems. The code is available at http://github.com/Tajamul21/TransFed