Federated Learning: Challenges, Methods, and Future Directions

Abstract

Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization, and privacy-preserving data analysis. In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work that are relevant to a wide range of research communities.

Affiliated Institutions

Carnegie Mellon University US

Related Publications

Advances and Open Problems in Federated Learning

Peter Kairouz , H. Brendan McMahan , Brendan Avent +49 more

Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a ...

2020 Foundations and Trends® in Machine Le... 3734 citations

Publication Info

Year: 2020
Type: article
Volume: 37
Issue: 3
Pages: 50-60
Citations: 3912
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Federated Learning: Challenges, Methods, and Future Directions

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

3912

OpenAlex

Cite This

APA Style

                            
                                
                                    Tian Li, 
                                
                                    Anit Kumar Sahu, 
                                
                                    Ameet Talwalkar
                                
                                et al.
                            
                            (2020). 
                            Federated Learning: Challenges, Methods, and Future Directions. 
                            IEEE Signal Processing Magazine
                            , 37
                            (3)
                            , 50-60.
                            https://doi.org/10.1109/msp.2020.2975749
                        

Identifiers

DOI: 10.1109/msp.2020.2975749