My focus is on personalized, collaborative and distributed data analytics, where knowledge from diverse data sources is effectively integrated. This approach allows sources to retain personalized models tailored to their unique features, distribute or decentralize model inference, and protect personal data when needed.
Currently, my research aims to answer three questions:
- Descriptive: How to extract what is shared and unique across datasets?
- Predictive: How can multiple entities (such as hospitals or IoT devices) collaboratively improve the predictive power of their models while keeping their personal data private?
- Prescriptive: How to fast-track and improve optimal design by effectively distributing trial & error efforts across collaborating entities?
Accomplishments and Awards
- 2021 Propelling Original Data Science (PODS) Grant Award: Coordinated Multi-building Modeling and Management for Flexible Grid Service Innovation
- New statistical tool to distinguish shared and unique features in data from different sources