Towards personalized federated learning

AZ Tan, H Yu, L Cui, Q Yang - IEEE transactions on neural …, 2022 - ieeexplore.ieee.org
In parallel with the rapid adoption of artificial intelligence (AI) empowered by advances in AI
research, there has been growing awareness and concerns of data privacy. Recent …

Model optimization techniques in personalized federated learning: A survey

F Sabah, Y Chen, Z Yang, M Azam, N Ahmad… - Expert Systems with …, 2024 - Elsevier
Personalized federated learning (PFL) is an exciting approach that allows machine learning
(ML) models to be trained on diverse and decentralized sources of data, while maintaining …

Federated learning and its role in the privacy preservation of IoT devices

T Alam, R Gupta - Future Internet, 2022 - mdpi.com
Federated learning (FL) is a cutting-edge artificial intelligence approach. It is a decentralized
problem-solving technique that allows users to train using massive data. Unprocessed …

Three approaches for personalization with applications to federated learning

Y Mansour, M Mohri, J Ro, AT Suresh - arxiv preprint arxiv:2002.10619, 2020 - arxiv.org
The standard objective in machine learning is to train a single model for all users. However,
in many learning scenarios, such as cloud computing and federated learning, it is possible …

No fear of heterogeneity: Classifier calibration for federated learning with non-iid data

M Luo, F Chen, D Hu, Y Zhang… - Advances in Neural …, 2021 - proceedings.neurips.cc
A central challenge in training classification models in the real-world federated system is
learning with non-IID data. To cope with this, most of the existing works involve enforcing …

Layer-wised model aggregation for personalized federated learning

X Ma, J Zhang, S Guo, W Xu - Proceedings of the IEEE/CVF …, 2022 - openaccess.thecvf.com
Abstract Personalized Federated Learning (pFL) not only can capture the common priors
from broad range of distributed data, but also support customized models for heterogeneous …

On bridging generic and personalized federated learning for image classification

HY Chen, WL Chao - arxiv preprint arxiv:2107.00778, 2021 - arxiv.org
Federated learning is promising for its capability to collaboratively train models with multiple
clients without accessing their data, but vulnerable when clients' data distributions diverge …

Federated reinforcement learning with environment heterogeneity

H **, Y Peng, W Yang, S Wang… - … Conference on Artificial …, 2022 - proceedings.mlr.press
Abstract We study Federated Reinforcement Learning (FedRL) problem in which $ n $
agents collaboratively learn a single policy without sharing the trajectories they collected …

Dynamic personalized federated learning with adaptive differential privacy

X Yang, W Huang, M Ye - Advances in Neural Information …, 2023 - proceedings.neurips.cc
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 …

A survey on heterogeneous federated learning

D Gao, X Yao, Q Yang - arxiv preprint arxiv:2210.04505, 2022 - arxiv.org
Federated learning (FL) has been proposed to protect data privacy and virtually assemble
the isolated data silos by cooperatively training models among organizations without …