paper-with-me

Papers

Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge Computing

2020-07-17 · Jed Mills, Jia Hu, Geyong Min

Federated Learning (FL) is an emerging approach for collaboratively training Deep Neural Networks (DNNs) on mobile devices, without private user data leaving the devices. Previous works have shown that non-Independent and Identically Distributed (non-IID) user data harms the convergence speed of the FL algorithms. Furthermore, most existing work on FL measures global-model accuracy, but in many cases, such as user content-recommendation, improving individual User model Accuracy (UA) is the real objective. To address these issues, we propose a Multi-Task FL (MTFL) algorithm that introduces non-federated Batch-Normalization (BN) layers into the federated DNN. MTFL benefits UA and convergence speed by allowing users to train models personalised to their own data. MTFL is compatible with popular iterative FL optimisation algorithms such as Federated Averaging (FedAvg), and we show empirically that a distributed form of Adam optimisation (FedAvg-Adam) benefits convergence speed even further when used as the optimisation strategy within MTFL. Experiments using MNIST and CIFAR10 demonstrate that MTFL is able to significantly reduce the number of rounds required to reach a target UA, by up to $5\times$ when using existing FL optimisation strategies, and with a further $3\times$ improvement when using FedAvg-Adam. We compare MTFL to competing personalised FL algorithms, showing that it is able to achieve the best UA for MNIST and CIFAR10 in all considered scenarios. Finally, we evaluate MTFL with FedAvg-Adam on an edge-computing testbed, showing that its convergence and UA benefits outweigh its overhead.

📄 PDF Abstract BibTeX arXiv:2007.09236

Code (1)

JedMills/MTFL-For-Personalised-DNNs 공식 구현 pytorch

Tasks

Edge-computingFederated Learning

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

Multi-task Federated Edge Learning (MtFEEL) in Wireless Networks

2021-08-05 · Sawan Singh Mahara, Shruti M., B. N. Bharath, Akash Murthy

Federated Learning (FL) has evolved as a promising technique to handle distributed machine learning across edge devices. A single neural network (NN) that optimises a global objective is generally learned in most work in…

Federated Learning

A novel parameter decoupling approach of personalized federated learning for image analysis

2023-05-15 · IET computer vision 2023 5 · Ruizheng Su, Xiongwen Pang, Hui Wang

Given the importance of privacy protection in databases and other institutions, federated learning (FL) is used to benefit training machine learning models based on these decentralised and private data so as to address t…

Federated LearningPersonalized Federated Learning

FedPop: A Bayesian Approach for Personalised Federated Learning

2022-06-07 · Nikita Kotelevskii, Maxime Vono, Eric Moulines, Alain Durmus

Personalised federated learning (FL) aims at collaboratively learning a machine learning model taylored for each client. Albeit promising advances have been made in this direction, most of existing approaches works do no…

Federated LearningUncertainty Quantification

FedCARE: A Multi-Objective Personalised Federated Learning Framework for Smart Healthcare

2026-08-04 · Rojalini Tripathy, Padmalochan Bera, Shreya Ghosh, Rajkumar Buyya arxiv

Federated Learning (FL) enables collaborative model training across distributed healthcare institutions without centralising sensitive patient data. However, real-world healthcare federations are often characterised not …

Federated Learning

Personalised Federated Learning On Heterogeneous Feature Spaces

2023-01-26 · Alain Rakotomamonjy, Maxime Vono, Hamlet Jesse Medina Ruiz, Liva Ralaivola

Most personalised federated learning (FL) approaches assume that raw data of all clients are defined in a common subspace i.e. all clients store their data according to the same schema. For real-world applications, this …

Federated Learning