Heterogeneous federated learning: State-of-the-art and research challenges
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 …
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 …
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
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 …
every iteration limiting the gradient norm to a certain value $ c> 0$. It is widely used for …
Mixed differential privacy in computer vision
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 …
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
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 …
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
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 …
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
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 …
training via multi-party computation and model aggregation. As a flexible learning setting …