Generalizable Federated Learning using Client Adaptive Focal Modulation
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
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
FedACT: Federated Adaptive Coordinate Trust Modulation for Robust Transformer Training under Data Heterogeneity
Federated Transformer training increasingly relies on local AdamW, whose adaptive updates can provide much stronger local progress than SGD-based training. However, under heterogeneous client data, even globally correcte…
FedLAM: Low-latency Wireless Federated Learning via Layer-wise Adaptive Modulation
In wireless federated learning (FL), the clients need to transmit the high-dimensional deep neural network (DNN) parameters through bandwidth-limited channels, which causes the communication latency issue. In this paper,…
Federated LearningFeDABoost: Fairness Aware Federated Learning with Adaptive Boosting
This work focuses on improving the performance and fairness of Federated Learning (FL) in non IID settings by enhancing model aggregation and boosting the training of underperforming clients. We propose FeDABoost, a nove…
Federated LearningFederated Vision Transformer with Adaptive Focal Loss for Medical Image Classification
While deep learning models like Vision Transformer (ViT) have achieved significant advances, they typically require large datasets. With data privacy regulations, access to many original datasets is restricted, especiall…
Medical Image ClassificationFederated LearningFederated Self-Supervised Learning for Automatic Modulation Classification under Non-IID and Class-Imbalanced Data
Training automatic modulation classification (AMC) models on centrally aggregated data raises privacy concerns, incurs communication overhead, and often fails to confer robustness to channel shifts. Federated learning (F…
Self-Supervised LearningRepresentation LearningFederated Learning