A state-of-the-art survey on solving non-iid data in federated learning

X Ma, J Zhu, Z Lin, S Chen, Y Qin - Future Generation Computer Systems, 2022 - Elsevier
Federated Learning (FL) proposed in recent years has received significant attention from
researchers in that it can enable multiple clients to cooperatively train global models without …

[PDF][PDF] A review of speech-centric trustworthy machine learning: Privacy, safety, and fairness

T Feng, R Hebbar, N Mehlman, X Shi… - … on Signal and …, 2023 - nowpublishers.com
Speech-centric machine learning systems have revolutionized a number of leading
industries ranging from transportation and healthcare to education and defense …

Auditing privacy defenses in federated learning via generative gradient leakage

Z Li, J Zhang, L Liu, J Liu - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
Federated Learning (FL) framework brings privacy benefits to distributed learning systems
by allowing multiple clients to participate in a learning task under the coordination of a …

Mime: Mimicking centralized stochastic algorithms in federated learning

SP Karimireddy, M Jaggi, S Kale, M Mohri… - arXiv preprint arXiv …, 2020 - arxiv.org
Federated learning (FL) is a challenging setting for optimization due to the heterogeneity of
the data across different clients which gives rise to the client drift phenomenon. In fact …

Breaking the centralized barrier for cross-device federated learning

SP Karimireddy, M Jaggi, S Kale… - Advances in …, 2021 - proceedings.neurips.cc
Federated learning (FL) is a challenging setting for optimization due to the heterogeneity of
the data across different clients which gives rise to the client drift phenomenon. In fact …

No fear of classifier biases: Neural collapse inspired federated learning with synthetic and fixed classifier

Z Li, X Shang, R He, T Lin… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Data heterogeneity is an inherent challenge that hinders the performance of federated
learning (FL). Recent studies have identified the biased classifiers of local models as the key …

On convergence of FedProx: Local dissimilarity invariant bounds, non-smoothness and beyond

X Yuan, P Li - Advances in Neural Information Processing …, 2022 - proceedings.neurips.cc
The\FedProx~ algorithm is a simple yet powerful distributed proximal point optimization
method widely used for federated learning (FL) over heterogeneous data. Despite its …

A comprehensive empirical study of heterogeneity in federated learning

AM Abdelmoniem, CY Ho… - IEEE Internet of …, 2023 - ieeexplore.ieee.org
Federated learning (FL) is becoming a popular paradigm for collaborative learning over
distributed, private data sets owned by nontrusting entities. FL has seen successful …

Resource-adaptive federated learning with all-in-one neural composition

Y Mei, P Guo, M Zhou, V Patel - Advances in Neural …, 2022 - proceedings.neurips.cc
Abstract Conventional Federated Learning (FL) systems inherently assume a uniform
processing capacity among clients for deployed models. However, diverse client hardware …

Training speech recognition models with federated learning: A quality/cost framework

D Guliani, F Beaufays, G Motta - ICASSP 2021-2021 IEEE …, 2021 - ieeexplore.ieee.org
We propose using federated learning, a decentralized on-device learning paradigm, to train
speech recognition models. By performing epochs of training on a per-user basis, federated …