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 …

Recent advances on federated learning: A systematic survey

B Liu, N Lv, Y Guo, Y Li - Neurocomputing, 2024 - Elsevier
Federated learning has emerged as an effective paradigm to achieve privacy-preserving
collaborative learning among different parties. Compared to traditional centralized learning …

Exploiting defenses against gan-based feature inference attacks in federated learning

X Luo, X Zhang - ar**: Stochastic bias and tight convergence guarantees
A Koloskova, H Hendrikx… - … Conference on Machine …, 2023 - proceedings.mlr.press
Gradient clip** is a popular modification to standard (stochastic) gradient descent, at
every iteration limiting the gradient norm to a certain value $ c> 0$. It is widely used for …

Mixed differential privacy in computer vision

A Golatkar, A Achille, YX Wang… - Proceedings of the …, 2022 - openaccess.thecvf.com
We introduce AdaMix, an adaptive differentially private algorithm for training deep neural
network classifiers using both private and public image data. While pre-training language …

Loki: Large-scale data reconstruction attack against federated learning through model manipulation

JC Zhao, A Sharma, AR Elkordy… - … IEEE Symposium on …, 2024 - ieeexplore.ieee.org
Federated learning was introduced to enable machine learning over large decentralized
datasets while promising privacy by eliminating the need for data sharing. Despite this, prior …

Normalized/clipped sgd with perturbation for differentially private non-convex optimization

X Yang, H Zhang, W Chen, TY Liu - arxiv preprint arxiv:2206.13033, 2022 - arxiv.org
By ensuring differential privacy in the learning algorithms, one can rigorously mitigate the
risk of large models memorizing sensitive training data. In this paper, we study two …

Emerging trends in federated learning: From model fusion to federated x learning

S Ji, Y Tan, T Saravirta, Z Yang, Y Liu… - International Journal of …, 2024 - Springer
Federated learning is a new learning paradigm that decouples data collection and model
training via multi-party computation and model aggregation. As a flexible learning setting …