DeepAI
Log In Sign Up

Adaptive Federated Dropout: Improving Communication Efficiency and Generalization for Federated Learning

11/08/2020
by   Nader Bouacida, et al.
0

With more regulations tackling users' privacy-sensitive data protection in recent years, access to such data has become increasingly restricted and controversial. To exploit the wealth of data generated and located at distributed entities such as mobile phones, a revolutionary decentralized machine learning setting, known as Federated Learning, enables multiple clients located at different geographical locations to collaboratively learn a machine learning model while keeping all their data on-device. However, the scale and decentralization of federated learning present new challenges. Communication between the clients and the server is considered a main bottleneck in the convergence time of federated learning. In this paper, we propose and study Adaptive Federated Dropout (AFD), a novel technique to reduce the communication costs associated with federated learning. It optimizes both server-client communications and computation costs by allowing clients to train locally on a selected subset of the global model. We empirically show that this strategy, combined with existing compression methods, collectively provides up to 57x reduction in convergence time. It also outperforms the state-of-the-art solutions for communication efficiency. Furthermore, it improves model generalization by up to 1.7

READ FULL TEXT
12/18/2018

Expanding the Reach of Federated Learning by Reducing Client Resource Requirements

Communication on heterogeneous edge networks is a fundamental bottleneck...
10/07/2021

Enabling On-Device Training of Speech Recognition Models with Federated Dropout

Federated learning can be used to train machine learning models on the e...
12/15/2021

LoSAC: An Efficient Local Stochastic Average Control Method for Federated Optimization

Federated optimization (FedOpt), which targets at collaboratively traini...
08/30/2022

Reducing Impacts of System Heterogeneity in Federated Learning using Weight Update Magnitudes

The widespread adoption of handheld devices have fueled rapid growth in ...
02/01/2023

: Downlink Compression for Cross-Device Federated Learning

Many compression techniques have been proposed to reduce the communicati...
12/12/2020

Communication-Efficient Federated Learning with Compensated Overlap-FedAvg

Petabytes of data are generated each day by emerging Internet of Things ...
02/02/2022

Communication Efficient Federated Learning for Generalized Linear Bandits

Contextual bandit algorithms have been recently studied under the federa...