ABSTRACT
To harness the benefits of machine learning (ML), users often face the challenge of sharing their private data with a central entity for model training. However, data sharing can be impractical due to privacy concerns, data size, wireless resource limitations, and other factors. Federated learning (FL) offers an efficient solution. In this approach, edge devices, users, or clients independently train machine learning models locally and iteratively share their model parameters with a central entity or server. The server aggregates these parameters into a global model, which is then distributed to all clients for the next round of training. Since the clients communicate with the server via wireless channels, over-the-air (OTA) computations have emerged as the optimal solution in the context of FL to resolve the challenge of aggregating local models. We investigate the influence of intrinsic noise introduced during OTA computations, focusing on the detrimental effects of impulsive noise on OTA-FL performance. Through a combination of theoretical analysis and experimental validation, we quantify the adverse impact of impulsive noise on convergence. We also introduce an algorithm designed to mitigate these effects. Our empirical results, obtained using CIFAR-10 and MNIST datasets, illustrate both the impact of impulsive noise on OTA-FL and the efficacy of our proposed solution.
- Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics. PMLR, 1273–1282.Google Scholar
- Tomer Sery, Nir Shlezinger, Kobi Cohen, and Yonina C Eldar. 2021. Over-the-air federated learning from heterogeneous data. IEEE Transactions on Signal Processing 69 (2021), 3796–3811.Google ScholarDigital Library
- K. Vastola. 1984. Threshold Detection in Narrow-Band Non-Gaussian Noise. IEEE Transactions on Communications 32, 2 (1984), 134–139. https://doi.org/10.1109/TCOM.1984.1096037Google ScholarCross Ref
Index Terms
- Enhancing Federated Learning Robustness in Wireless Networks
Recommendations
Improved bilateral filter for suppressing mixed noise in color images
It is a challenging problem to suppress mixed noise in color images. The traditional bilateral filter can excellently reduce additive noise without destroying image edges and details, but it fails to remove impulsive noise. This paper presents an ...
Short Communication: Multichannel image processing by using the Rank M-type L-filter
In this paper, we introduce the Vector Rank M-type L (VRML)-filter to remove impulsive noise from color images and video sequences. The proposed filter uses the Median M-type (MM) and Ansari-Bradley-Siegel-Tukey M-type (AM) estimators into L-filter to ...
Federated Learning Strategies Over Wireless Channels
Internet of Things, Smart Spaces, and Next Generation Networks and SystemsAbstractMachine learning over distributed data collected by many clients has important applications in use cases where data privacy is a key concern or central data storage is not an option. Federated learning has introduced solutions for these scenarios, ...
Comments