Add to ORKGInternational audienceThis work addresses the problem of optimizing communications between server and clients in federated learning (FL). Current sampling approaches in FL are either biased, or non optimal in terms of server-clients communications and training stability. To overcome this issue, we introduce clustered sampling for clients selection. We prove that clustered sampling leads to better clients representatitivity and to reduced variance of the clients stochastic aggregation weights in FL. Compatibly with our theory, we provide two different clustering approaches enabling clients aggregation based on 1) sample size, and 2) models similarity. Through a series of experiments in non-iid and unbalanced scenarios, we demonstrate that mo...
As a privacy-preserving paradigm for training Machine Learning (ML) models, Federated Learning (FL) ...
International audienceFederated learning enables different parties to collaboratively build a global...
Federated learning (FL) has been proposed as a privacy-preserving approach in distributed machine le...
International audienceWhile client sampling is a central operation of current state-of-the-art feder...
Graduate School of Artificial Intelligence ArtificiFederated learning is a privacy-preserving machin...
Federated Learning (FL) provides a promising solution for preserving privacy in learning shared mode...
Federated learning deals with the challenge of accessing data from different information sources whi...
Federated learning deals with the challenge of accessing data from different information sources whi...
Federated learning (FL) has been proposed as a machine learning approach to collaboratively learn a ...
Federated learning (FL) is a distributed machine learning paradigm that selects a subset of clients ...
Knowledge sharing and model personalization are essential components to tackle the non-IID challenge...
The advent of machine learning techniques has given rise to modern devices with built-in models for ...
The advent of machine learning techniques has given rise to modern devices with built-in models for ...
Personalized decision-making can be implemented in a Federated learning (FL) framework that can coll...
Federated Learning (FL) is a machine learning setting where many devices collaboratively train a mac...
As a privacy-preserving paradigm for training Machine Learning (ML) models, Federated Learning (FL) ...
International audienceFederated learning enables different parties to collaboratively build a global...
Federated learning (FL) has been proposed as a privacy-preserving approach in distributed machine le...
International audienceWhile client sampling is a central operation of current state-of-the-art feder...
Graduate School of Artificial Intelligence ArtificiFederated learning is a privacy-preserving machin...
Federated Learning (FL) provides a promising solution for preserving privacy in learning shared mode...
Federated learning deals with the challenge of accessing data from different information sources whi...
Federated learning deals with the challenge of accessing data from different information sources whi...
Federated learning (FL) has been proposed as a machine learning approach to collaboratively learn a ...
Federated learning (FL) is a distributed machine learning paradigm that selects a subset of clients ...
Knowledge sharing and model personalization are essential components to tackle the non-IID challenge...
The advent of machine learning techniques has given rise to modern devices with built-in models for ...
The advent of machine learning techniques has given rise to modern devices with built-in models for ...
Personalized decision-making can be implemented in a Federated learning (FL) framework that can coll...
Federated Learning (FL) is a machine learning setting where many devices collaboratively train a mac...
As a privacy-preserving paradigm for training Machine Learning (ML) models, Federated Learning (FL) ...
International audienceFederated learning enables different parties to collaboratively build a global...
Federated learning (FL) has been proposed as a privacy-preserving approach in distributed machine le...