Adaptive Test-Time Personalization for Federated Learning
Personalized federated learning algorithms have shown promising results in adapting models to various distribution shifts. However, most of these methods require labeled data on testing clients for personalization, which is usually unavailable in real-world scenarios. In this paper, we introduce a novel setting called test-time personalized federated learning (TTPFL), where clients locally adapt a global model in an unsupervised way without relying on any labeled data during test-time. While traditional test-time adaptation (TTA) can be used in this scenario, most of them inherently assume training data come from a single domain, while they come from multiple clients (source domains) with different distributions. Overlooking these domain interrelationships can result in suboptimal generalization. Moreover, most TTA algorithms are designed for a specific kind of distribution shift and lack the flexibility to handle multiple kinds of distribution shifts in FL. In this paper, we find that this lack of flexibility partially results from their pre-defining which modules to adapt in the model. To tackle this challenge, we propose a novel algorithm called ATP to adaptively learns the adaptation rates for each module in the model from distribution shifts among source domains. Theoretical analysis proves the strong generalization of ATP. Extensive experiments demonstrate its superiority in handling various distribution shifts including label shift, image corruptions, and domain shift, outperforming existing TTA methods across multiple datasets and model architectures. Our code is available at https://github.com/baowenxuan/ATP .
Code (1)
Tasks
Federated LearningPersonalized Federated LearningTest-time AdaptationSimilar Papers 제목 키워드 기반
FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization
Test-time personalization in federated learning enables models at clients to adjust online to local domain shifts, enhancing robustness and personalization in deployment. Yet, existing federated learning work largely ove…
Federated LearningDual-Personalizing Adapter for Federated Foundation Models
Recently, foundation models, particularly large language models (LLMs), have demonstrated an impressive ability to adapt to various tasks by fine-tuning diverse instruction data. Notably, federated foundation models (Fed…
Federated LearningFedPC: Federated Learning for Language Generation with Personal and Context Preference Embeddings
Federated learning is a training paradigm that learns from multiple distributed users without aggregating data on a centralized server. Such a paradigm promises the ability to deploy machine-learning at-scale to a divers…
Federated LearningText GenerationProfit: Benchmarking Personalization and Robustness Trade-off in Federated Prompt Tuning
In many applications of federated learning (FL), clients desire models that are personalized using their local data, yet are also robust in the sense that they retain general global knowledge. However, the presence of da…
BenchmarkingFederated LearningGeneral KnowledgeNavigate+1Dynamic Personalized Federated Learning with Adaptive Differential Privacy
Personalized federated learning with differential privacy has been considered a feasible solution to address non-IID distribution of data and privacy leakage risks. However, current personalized federated learning method…