Data Science Research Group: Federated learning

Federated learning

Description

Federated learning is an sub-area of machine learning that focuses on providing distributed and scalable algorithms for training models across multiple decentralized peers without the need for sharing or exchanging data or information.

Latest publications

	Distributed safe resource allocation using barrier functions Wu, Xuyang, Magnússon, Sindri, and Johansson, Mikael Automatica, 2023
	Energy-Efficient and Adaptive Gradient Sparsification for Federated Learning Vaishnav, Shubham, Efthymiou, Maria, and Magnússon, Sindri In ICC 2023-IEEE International Conference on Communications, 2023
	Eco-Fedsplit: Federated Learning with Error-Compensated Compression Khirirat, Sarit, Magnússon, Sindri, and Johansson, Mikael In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022
	A flexible framework for communication-efficient machine learning Khirirat, S., Magnússon, S., Aytekin, A., and Johansson, M. In Proceedings of The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21), 2021
	Compressed Gradient Methods with Hessian-Aided Error Compensation Khirirat, S., Magnússon, S., and Johansson, M. IEEE Transactions on Signal Processing, 2021
	The Internet of Things as a Deep Neural Network Du, R., Magnússon, S., and Fischione, C. IEEE Communications Magazine, Internet of Things and Sensor Networks Series, 2020
	Communication-Efficient Variance-Reduced Stochastic Gradient Descent Shokri-Ghadikolaei, H., and Magnússon, S. In Proceedings of the IFAC World Congress, 2020
	On Maintaining Linear Convergence of Distributed Learning and Optimization under Limited Communication Magnússon, Sindri, Shokri-Ghadikolaei, Hossein, and Li, Na IEEE Transactions on Signal Processing, 2020
	Convergence Bounds For Compressed Gradient Methods With Memory Based Error Compensation Khirirat, S., Magnússon, S., and Johansson, M. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019
	On Maintaining Linear Convergence of Distributed Learning and Optimization under Limited Communication Magnússon, S., Shokri-Ghadikolaei, H., and N. Li, In Proceedings of the 53rd IEEE Asilomar Conference on Signals, Systems, and Computers, 2019
	Communication Complexity of Dual Decomposition Methods for Distributed Resource Allocation Optimization Magnússon, S., Enyioha, C., Li, N., Fischione, C., and Tarokh, V. IEEE Journal of Selected Topics in Signal Processing, 2018
	Convergence of Limited Communications Gradient Methods Magnússon, S., Enyioha, C., Li, N., Fischione, C., and Tarokh, V. IEEE Transactions on Automatic Control, 2018
	On the Convergence of Alternating Direction Lagrangian Methods for Nonconvex Structured Optimization Problems Magnússon, S., Weeraddana, P. C., Rabbat, M. G., and Fischione, C. IEEE Transactions on Control of Network Systems, 2016
	Practical Coding Schemes For Bandwidth Limited One-Way Communication Resource Allocation Magnússon, S., Enyioha, C., Fischione, C., and Li, N. In Proceedings of the 56th IEEE Conference on Decision and Control (CDC), 2016
	Convergence of Limited Communications Gradient Method Magnússon, S., Enyioha, C., Li, N., Fischione, C., and Tarokh, V. In Proceedings of the IEEE American Control Conference (ACC), 2016
	Analysis for an Online Decentralized Descent Power allocation algorithm Enyioha, C., Magnússon, S., Heal, K., Li, N., Fischione, C., and Tarokh, V. In Proceedings of the IEEE Information Theory and Applications Workshop (ITA), 2016
	On the Convergence of an Alternating Direction Penalty Method for Nonconvex Problems Magnússon, S., Weeraddana, P. C., Rabbat, M. G., and Fischione, C. In Proceedings of the IEEE 48th Asilomar Conference on Signals, Systems and Computers , 2015

People

Sindri Magnússon, Associate Professor

distributed optimization, reinforcement learning, federated learning, IoT/CPS

Ali Beikmohammadi

efficient federated learning in complex networks

Shubham Vaishnav

reinforcement learning, federated learning, fog and edge networks optimization

Lena Mondrejevski

federated learning (Getinge)

Mohsen Amiri

reinforcement learning, federated learning, distributed optimization