Federated Learning: A Signal Processing Perspective
This work addresses privacy and scalability problems for edge device users in federated learning, but it is incremental as it primarily surveys and adapts existing signal processing methods rather than introducing new paradigms.
The paper tackles the challenge of training machine learning models across multiple edge devices without sharing data due to privacy concerns, by providing a unified framework from a signal processing perspective to address core issues like communication and data heterogeneity. It surveys and adapts signal processing tools to facilitate federated learning at scale, aiming to transition deep learning from centralized servers to mobile edge devices.
The dramatic success of deep learning is largely due to the availability of data. Data samples are often acquired on edge devices, such as smart phones, 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 datasets, 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. In this article, we provide a unified systematic framework for federated learning in a manner that encapsulates and highlights the main challenges that are natural to treat using signal processing tools. We present a formulation for the federated learning paradigm from a signal processing perspective, and survey a set of candidate approaches for tackling its unique challenges. We further provide guidelines for the design and adaptation of signal processing and communication methods to facilitate federated learning at large scale.