My Research Journey to Sweden (Karlskrona)

Abstract: Modern mobile devices have access to a wealth of data suitable for learning models, which in turn can greatly improve the user experience. For example, language models can improve speech recognition and text entry, and image models can automatically select good photos. However, this rich data is often privacy sensitive, large in quantity, or both, which may preclude logging to the data center and training there using conventional approaches. We advocate an alternative that leaves the training data distributed on the mobile devices, and learns a shared model by aggregating locally-computed updates...

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...

Abstract: Federated learning (FL) is a distributed machine learning paradigm that enables a large number of clients to collaboratively learn a shared model while keeping their data locally. To enhance privacy, FL is commonly combined with differential privacy (DP), which offers a mathematically rigorous notion of privacy with well-established statistical properties...