Statistical inference and machine-learning algorithms have traditionally been developed for data available at a single location. Unlike this centralized setting, modern data sets are …
Decentralised learning is attracting more and more interest because it embodies the principles of data minimisation and focused data collection, while favouring the transparency …
C Fang, Z Yang, WU Bajwa - IEEE Transactions on Signal and …, 2022 - ieeexplore.ieee.org
Machine learning has begun to play a central role in many applications. A multitude of these applications typically also involve datasets that are distributed across multiple computing …
R Schlegel, S Kumar, E Rosnes… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
We present two novel federated learning (FL) schemes that mitigate the effect of straggling devices by introducing redundancy on the devices' data across the network. Compared to …
Z Chen, P Tian, W Liao, W Yu - IEEE Transactions on Network …, 2020 - ieeexplore.ieee.org
The simultaneous development of deep learning techniques and Internet of Things (IoT)/Cyber-physical Systems (CPS) technologies has afforded untold possibilities for …
R Guerraoui, S Rouault - International Conference on …, 2018 - proceedings.mlr.press
While machine learning is going through an era of celebrated success, concerns have been raised about the vulnerability of its backbone: stochastic gradient descent (SGD). Recent …
C Fung, CJM Yoon, I Beschastnikh - arXiv preprint arXiv:1808.04866, 2018 - arxiv.org
Machine learning (ML) over distributed multi-party data is required for a variety of domains. Existing approaches, such as federated learning, collect the outputs computed by a group of …
The widespread use of mobile devices, as well as the increasing popularity of mobile services has raised serious cybersecurity challenges. In the last years, the number of …
Y Chen, L Su, J Xu - Proceedings of the ACM on Measurement and …, 2017 - dl.acm.org
We consider the distributed statistical learning problem over decentralized systems that are prone to adversarial attacks. This setup arises in many practical applications, including …