Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints

10/04/2019
by   Felix Sattler, et al.
42

Federated Learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit it's popularity, it has been observed that Federated Learning yields suboptimal results if the local clients' data distributions diverge. To address this issue, we present Clustered Federated Learning (CFL), a novel Federated Multi-Task Learning (FMTL) framework, which exploits geometric properties of the FL loss surface, to group the client population into clusters with jointly trainable data distributions. In contrast to existing FMTL approaches, CFL does not require any modifications to the FL communication protocol to be made, is applicable to general non-convex objectives (in particular deep neural networks) and comes with strong mathematical guarantees on the clustering quality. CFL is flexible enough to handle client populations that vary over time and can be implemented in a privacy preserving way. As clustering is only performed after Federated Learning has converged to a stationary point, CFL can be viewed as a post-processing method that will always achieve greater or equal performance than conventional FL by allowing clients to arrive at more specialized models. We verify our theoretical analysis in experiments with deep convolutional and recurrent neural networks on commonly used Federated Learning datasets.

READ FULL TEXT
research
02/13/2022

On the Convergence of Clustered Federated Learning

In a federated learning system, the clients, e.g. mobile devices and org...
research
03/02/2023

Stochastic Clustered Federated Learning

Federated learning is a distributed learning framework that takes full a...
research
02/15/2023

A Federated Learning Benchmark for Drug-Target Interaction

Aggregating pharmaceutical data in the drug-target interaction (DTI) dom...
research
06/05/2023

Unlocking the Potential of Federated Learning for Deeper Models

Federated learning (FL) is a new paradigm for distributed machine learni...
research
09/20/2023

Clustered FedStack: Intermediate Global Models with Bayesian Information Criterion

Federated Learning (FL) is currently one of the most popular technologie...
research
05/07/2021

Towards Practical Watermark for Deep Neural Networks in Federated Learning

With the wide application of deep neural networks, it is important to ve...
research
03/21/2020

Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning

Federated learning (FL) is a novel machine learning setting which enable...

Please sign up or login with your details

Forgot password? Click here to reset