Advances and Open Problems in Federated Learning

Authors:

PKPeter Kairouz
Peter Kairouz
HMH. Brendan McMahan
H. Brendan McMahan
KBKeith Bonawitz
Keith Bonawitz

Preprint

Publisher website

Google Scholar

8 March 2021

preprint
Published by arXiv in arXiv

DOI:https://doi.org/10.48550/arXiv.1912.04977

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

FEDERATED LEARNING
LEARNING FEDERATED
SERVICE PROVIDER
MOBILE DEVICES
COLLABORATIVELY TRAIN
CENTRAL SERVER
MACHINE LEARNING
OPEN PROBLEMS
LEARNING SETTING
FEDERATED

All Related Versions

Version 1, 2019-12-10, ArXiv
Version 2, 2021-03-08, ArXiv
Version 3, 2021-03-09, ArXiv

This publication has 80 references indexed in Scilit:

Private Join and Compute from PIR with Default
2021
Turning HATE into LOVE: Compact Homomorphic Ad Hoc Threshold Encryption for Scalable MPC
2021
On the Power of Multiple Anonymous Messages: Frequency Estimation and Selection in the Shuffle Model of Differential Privacy
2021
Private Information Retrieval with Sublinear Online Time
2020
Private Aggregation from Fewer Anonymous Messages
2020
The Privacy Blanket of the Shuffle Model
2019
Zero-Knowledge Proofs on Secret-Shared Data via Fully Linear PCPs
2019
Fast Homomorphic Evaluation of Deep Discretized Neural Networks
2018
Evasion Attacks against Machine Learning at Test Time
2013
Pioneer: Verifying Code Integrity and Enforcing Untampered Code Execution on Legacy Systems
2007