Communication-Efficient Learning of Deep Networks from Decentralized Data, H. Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, Blaise Agüera y Arcas, 2017Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), Vol. 54 (JMLR.org)DOI: 10.5555/3305890.3305967 - Introduces Federated Averaging (FedAvg), a core FL algorithm, and highlights communication efficiency as a critical evaluation aspect.
Advances and Open Problems in Federated Learning, Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Grifo, Dimitri Lepage, Justin Michaels, Arjun Nandi, Ananda Theertha Suresh, Sewoong Oh, Felix X. Yu, 2021Foundations and Trends® in Machine Learning, Vol. 14 (Now Publishers)DOI: 10.1561/2200000083 - This survey provides a broad overview of FL, including discussions on statistical and systems heterogeneity, privacy, fairness, and evaluation challenges.
Learning with Differential Privacy, Martin Abadi, Andy Chu, Ian Goodfellow, H. Brendan McMahan, Ilya Mironov, Kunal Talwar, Li Zhang, 2016Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, CCS '16 (ACM)DOI: 10.1145/2976749.2978318 - Introduces differentially private stochastic gradient descent (DP-SGD), a fundamental method for achieving formal privacy guarantees in machine learning, relevant to FL privacy assessment.