paper-with-me

홈 › Papers

Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions

2025-05-21 · Hossein Zakerinia, Jonathan Scott, Christoph H. Lampert

Personalized federated learning has emerged as a popular approach to training on devices holding statistically heterogeneous data, known as clients. However, most existing approaches require a client to have labeled data for training or finetuning in order to obtain their own personalized model. In this paper we address this by proposing FLowDUP, a novel method that is able to generate a personalized model using only a forward pass with unlabeled data. The generated model parameters reside in a low-dimensional subspace, enabling efficient communication and computation. FLowDUP's learning objective is theoretically motivated by our new transductive multi-task PAC-Bayesian generalization bound, that provides performance guarantees for unlabeled clients. The objective is structured in such a way that it allows both clients with labeled data and clients with only unlabeled data to contribute to the training process. To supplement our theoretical results we carry out a thorough experimental evaluation of FLowDUP, demonstrating strong empirical performance on a range of datasets with differing sorts of statistically heterogeneous clients. Through numerous ablation studies, we test the efficacy of the individual components of the method.

📄 PDF Abstract BibTeX arXiv:2505.15579

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningPersonalized Federated Learning

Similar Papers 제목 키워드 기반

QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning

2021-07-29 · NeurIPS 2021 12 · Kaan Ozkara, Navjot Singh, Deepesh Data, Suhas Diggavi

Traditionally, federated learning (FL) aims to train a single global model while collaboratively using multiple clients and a server. Two natural challenges that FL algorithms face are heterogeneity in data across client…

Federated LearningKnowledge DistillationModel CompressionQuantization

FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy

2023-07-01 · Jianqing Zhang, Yang Hua, Hao Wang, Tao Song 외

Recently, personalized federated learning (pFL) has attracted increasing attention in privacy protection, collaborative learning, and tackling statistical heterogeneity among clients, e.g., hospitals, mobile smartphones,…

Federated LearningPersonalized Federated Learning

Federated Unsupervised Visual Representation Learning via Exploiting General Content and Personal Style

2022-11-11 · Yuewei Yang, Jingwei Sun, Ang Li, Hai Li 외

Discriminative unsupervised learning methods such as contrastive learning have demonstrated the ability to learn generalized visual representations on centralized data. It is nonetheless challenging to adapt such methods…

Contrastive LearningFederated LearningRepresentation Learning

Survey of Personalization Techniques for Federated Learning

2020-03-19 · Viraj Kulkarni, Milind Kulkarni, Aniruddha Pant

Federated learning enables machine learning models to learn from private decentralized data without compromising privacy. The standard formulation of federated learning produces one shared model for all clients. Statisti…

BIG-bench Machine LearningFederated LearningSurvey

QuPeL: Quantized Personalization with Applications to Federated Learning

2021-02-23 · Kaan Ozkara, Navjot Singh, Deepesh Data, Suhas Diggavi

Traditionally, federated learning (FL) aims to train a single global model while collaboratively using multiple clients and a server. Two natural challenges that FL algorithms face are heterogeneity in data across client…

DiversityFederated LearningQuantization