Heterogeneous federated learning: State-of-the-art and research challenges

M Ye, X Fang, B Du, PC Yuen, D Tao - ACM Computing Surveys, 2023 - dl.acm.org
Federated learning (FL) has drawn increasing attention owing to its potential use in large-
scale industrial applications. Existing FL works mainly focus on model homogeneous …

A systematic literature review on federated machine learning: From a software engineering perspective

SK Lo, Q Lu, C Wang, HY Paik, L Zhu - ACM Computing Surveys (CSUR …, 2021 - dl.acm.org
Federated learning is an emerging machine learning paradigm where clients train models
locally and formulate a global model based on the local model updates. To identify the state …

Dispfl: Towards communication-efficient personalized federated learning via decentralized sparse training

R Dai, L Shen, F He, X Tian, D Tao - arxiv preprint arxiv:2206.00187, 2022 - arxiv.org
Personalized federated learning is proposed to handle the data heterogeneity problem
amongst clients by learning dedicated tailored local models for each user. However, existing …

Federated learning with cooperating devices: A consensus approach for massive IoT networks

S Savazzi, M Nicoli, V Rampa - IEEE Internet of Things Journal, 2020 - ieeexplore.ieee.org
Federated learning (FL) is emerging as a new paradigm to train machine learning (ML)
models in distributed systems. Rather than sharing and disclosing the training data set with …

Decentralized federated averaging

T Sun, D Li, B Wang - IEEE Transactions on Pattern Analysis …, 2022 - ieeexplore.ieee.org
Federated averaging (FedAvg) is a communication-efficient algorithm for distributed training
with an enormous number of clients. In FedAvg, clients keep their data locally for privacy …

Topology-aware federated learning in edge computing: A comprehensive survey

J Wu, F Dong, H Leung, Z Zhu, J Zhou… - ACM Computing …, 2024 - dl.acm.org
The ultra-low latency requirements of 5G/6G applications and privacy constraints call for
distributed machine learning systems to be deployed at the edge. With its simple yet …

Promptfl: Let federated participants cooperatively learn prompts instead of models-federated learning in age of foundation model

T Guo, S Guo, J Wang, X Tang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Quick global aggregation of effective distributed parameters is crucial to federated learning
(FL), which requires adequate bandwidth for parameters communication and sufficient user …

Improving the model consistency of decentralized federated learning

Y Shi, L Shen, K Wei, Y Sun, B Yuan… - International …, 2023 - proceedings.mlr.press
To mitigate the privacy leakages and communication burdens of Federated Learning (FL),
decentralized FL (DFL) discards the central server and each client only communicates with …

Federated quantum machine learning

SYC Chen, S Yoo - Entropy, 2021 - mdpi.com
Distributed training across several quantum computers could significantly improve the
training time and if we could share the learned model, not the data, it could potentially …

[HTML][HTML] Decentralized learning works: An empirical comparison of gossip learning and federated learning

I Hegedűs, G Danner, M Jelasity - Journal of Parallel and Distributed …, 2021 - Elsevier
Abstract Machine learning over distributed data stored by many clients has important
applications in use cases where data privacy is a key concern or central data storage is not …