Optimal MIMO Combining for Blind Federated Edge Learning with Gradient Sparsification
Not on the map. Why?
Abstract (arXiv)
We provide the optimal receive combining strategy for federated learning in multiple-input multiple-output (MIMO) systems. Our proposed algorithm allows the clients to perform individual gradient sparsification which greatly improves performance in scenarios with heterogeneous (non i.i.d.) training data. The proposed method beats the benchmark by a wide margin.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Mar 2022.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 1; 2023: 2; 2024: 1.
4 papers.
- 2022A Survey on Over-the-Air Computationcited by 19
- 2023Communication Trade-offs in Federated Learning of Spiking Neural Networkscited by 1
- 2023Over-the-Air Federated Learning with Compressed Sensing: Is Sparsification Necessary?cited by 1
- 2024Efficient Wireless Federated Learning via Low-Rank Gradient Factorizationcited by 0
- 2024Efficient Wireless Federated Learning via Low-Rank Gradient Factorization15 Jan 2024
- 2023Over-the-Air Federated Learning with Compressed Sensing: Is Sparsification Necessary?5 Oct 2023
- 2023Communication Trade-offs in Federated Learning of Spiking Neural Networks27 Feb 2023
- 2022A Survey on Over-the-Air Computation20 Oct 2022