Federated Learning: A signal processing perspective

doi:10.1109/MSP.2021.3125282

Federated Learning: A signal processing perspective

2022-05-01

58

OA

AI

DOI：10.1109/MSP.2021.3125282

Original

Original request for help

Save

Abstract

En 中文

The dramatic success of deep learning is largely due to the availability of data. Data samples are often acquired on edge devices, such as smartphones, vehicles, and sensors, and in some cases cannot be shared due to privacy considerations. Federated learning is an emerging machine learning paradigm for training models across multiple edge devices holding local data sets, without explicitly exchanging the data. Learning in a federated manner differs from conventional centralized machine learning and poses several core unique challenges and requirements, which are closely related to classical problems studied in the areas of signal processing and communications. Consequently, dedicated schemes derived from these areas are expected to play an important role in the success of federated learning and the transition of deep learning from the domain of centralized servers to mobile edge devices.

Keywords:

Deep learning

Training

Data privacy

Signal processing

Collaborative work

Data models

Sensors

Federated Learning: A signal processing perspective

Abstract

Journal

Organization