Zero-Shot Decentralized Federated Learning
CLIP has revolutionized zero-shot learning by enabling task generalization without fine-tuning. While prompting techniques like CoOp and CoCoOp enhance CLIP's adaptability, their effectiveness in Federated Learning (FL) remains an open challenge. Existing federated prompt learning approaches, such as FedCoOp and FedTPG, improve performance but face generalization issues, high communication costs, and reliance on a central server, limiting scalability and privacy. We propose Zero-shot Decentralized Federated Learning (ZeroDFL), a fully decentralized framework that enables zero-shot adaptation across distributed clients without a central coordinator. ZeroDFL employs an iterative prompt-sharing mechanism, allowing clients to optimize and exchange textual prompts to enhance generalization while drastically reducing communication overhead. We validate ZeroDFL on nine diverse image classification datasets, demonstrating that it consistently outperforms--or remains on par with--state-of-the-art federated prompt learning methods. More importantly, ZeroDFL achieves this performance in a fully decentralized setting while reducing communication overhead by 118x compared to FedTPG. These results highlight that our approach not only enhances generalization in federated zero-shot learning but also improves scalability, efficiency, and privacy preservation--paving the way for decentralized adaptation of large vision-language models in real-world applications.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ClassificationFederated LearningZero-Shot LearningSimilar Papers 제목 키워드 기반
FedVLM: Scalable Personalized Vision-Language Models through Federated Learning
Vision-language models (VLMs) demonstrate impressive zero-shot and few-shot learning capabilities, making them essential for several downstream tasks. However, fine-tuning these models at scale remains challenging, parti…
Federated LearningFew-Shot LearningWhen to Stop Federated Learning: Zero-Shot Generation of Synthetic Validation Data with Generative AI for Early Stopping
Federated Learning (FL) enables collaborative model training across decentralized devices while preserving data privacy. However, FL methods typically run for a predefined number of global rounds, often leading to unnece…
Federated LearningFederated Zero-Shot Learning for Visual Recognition
Zero-shot learning is a learning regime that recognizes unseen classes by generalizing the visual-semantic relationship learned from the seen classes. To obtain an effective ZSL model, one may resort to curating training…
Federated LearningZero-Shot LearningTowards Fair Federated Learning with Zero-Shot Data Augmentation
Federated learning has emerged as an important distributed learning paradigm, where a server aggregates a global model from many client-trained models while having no access to the client data. Although it is recognized …
Data AugmentationFairnessFederated LearningFederated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments
In federated learning, all networked clients contribute to the model training cooperatively. However, with model sizes increasing, even sharing the trained partial models often leads to severe communication bottlenecks i…
Dataset DistillationFederated Learning