Federated Learning (FL) (McMahan et al., 2017) is a dis-tributed machine learning approach which enables trainingon a large corpus of decentralized data residing on deviceslike mobile phones. FL is one instance of the more generalapproach of “bringing the code to the data, instead of thedata to the code” and addresses the fundamental problemsof privacy, ownership, and locality of data. The generaldescription of FL has been given by McMahan & Ramage(2017), and its theory has been explored in Koneˇcn ́y et al.(2016a); McMahan et al. (2017; 2018). Read More
Daily Archives: March 21, 2019
Data Transparent ML + Health Privacy vs Societal Benefits Training NN without Raw Data
Split Learning versus Federated Learning for Data Transparent ML, Camera Culture Group, MIT Media Lab. SlideShare Briefing. Read More
No Peek: A Survey of private distributed deep learning
A survey of distributed deep learning models for training or inference without accessing raw data from clients. These methods aim to protect confidential patterns in data while still allowing servers to train models. The distributed deep learning methods of federated learning, split learning and large batch stochastic gradient descent are compared in addition to private and secure approaches of differential privacy, homomorphic encryption, oblivious transfer and garbled circuits in the context of neural networks. We study their benefits, limitations and trade-offs with regards to computational resources, data leakage and communication efficiency and also share our anticipated future trends. Read More
Rick's Cafe AI 