[1912.04977v1] Advances and Open Problems in Federated Learning
The workshop had a more algorithmic flavor, and so systems-related research topics are somewhat less well represented, despite the fact that building systems for federated learning is a fundamentally important and challenging problem
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.
‹Figure 1: The lifecycle of an FL-trained model and the various actors in a federated learning system. This figure is revisited in ?? from a threat models perspective. (Introduction) (Preserving the Privacy of User Data)Figure 3: The Encode-Shuffle-Analyze (ESA) framework, illustrated here for 4 players. (Privacy-Preserving Disclosures)›