Advances and Open Problems in Federated Learning

Abstract

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 central server (e.g. service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.

Keywords

OrchestrationComputer scienceData collectionFederated learningOpen researchService providerData scienceService (business)Artificial intelligenceWorld Wide WebBusiness

Affiliated Institutions

Google (United States) US

Related Publications

Federated Learning: Challenges, Methods, and Future Directions

Tian Li , Anit Kumar Sahu , Ameet Talwalkar +5 more

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...

2020 IEEE Signal Processing Magazine 3912 citations

Publication Info

Year: 2020
Type: article
Volume: 14
Issue: 1–2
Pages: 1-210
Citations: 3734
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Advances and Open Problems in Federated Learning

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

3734

OpenAlex

Cite This

APA Style

                            
                                
                                    Peter Kairouz, 
                                
                                    H. Brendan McMahan, 
                                
                                    Brendan Avent
                                
                                et al.
                            
                            (2020). 
                            Advances and Open Problems in Federated Learning. 
                            Foundations and Trends® in Machine Learning
                            , 14
                            (1–2)
                            , 1-210.
                            https://doi.org/10.1561/2200000083
                        

Identifiers

DOI: 10.1561/2200000083