1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.
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.
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 address 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 the concept’s unique challenges. We further provide guidelines for the design and adaptation of signal processing and communication methods to facilitate federated learning at a large scale.
Machine learning has led to breakthroughs in various fields, such as natural language processing, computer vision, and speech recognition. Since machine learning methods, and particularly those based on deep neural networks (DNNs), are data driven, their success hinges on vast amounts of training data. These data are commonly generated at edge devices, including mobile phones, sensors, vehicles, and medical devices. In the traditional cloud-centric approach, data collected by mobile devices are uploaded and processed centrally at a cloud-based server or data center. Because data sets, such as images and text messages, often contain private information, uploading them may be undesirable due to privacy and locality concerns. Furthermore, sharing massive data sets can result in a substantial burden on the communication links between the edge devices and the server.