The widespread use of smartphones and wearables, such as Fitbits, facilitates data collection at a previously unobtainable scale. This enables the use of modern machine learning methods to build complex predictive models. However, the ubiquitous nature of this data requires stronger privacy protection compared to more targeted health monitoring. One method to address user privacy while taking advantage of sharing data across users is federated learning, a technique which allows a machine learning model to be trained using data from all users, while only storing a user’s data on that user's device. By keeping data on individual user devices, we protect the user’s private data from data leaks and breaches on the researcher’s central server, and provide users with more control over how and when their data is used.
(joint work with Jessica Liu, Jack Goetz, and Prof. Srijan Sen's lab)