FedControl: When Control Theory Meets Federated Learning
Not on the map. Why?
Abstract (arXiv)
To date, the most popular federated learning algorithms use coordinate-wise averaging of the model parameters. We depart from this approach by differentiating client contributions according to the performance of local learning and its evolution. The technique is inspired from control theory and its classification performance is evaluated extensively in IID framework and compared with FedAvg.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 8 of its 9 references that are in the map. First posted on arXiv 27 May 2022.
Builds on
8 of 9 references.
References · 8
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
- 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
- 2019SGD: General Analysis and Improved Ratescited by 206
- 2021A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparisoncited by 31
- 2021FedPAGE: A Fast Local Stochastic Gradient Method for Communication-Efficient Federated Learningcited by 19
- 2021FedCostWAvg: A new averaging for better Federated Learningcited by 11
Built on by
Not cited yet.