José Luis Ambite

Accelerating Federated Learning in Heterogeneous Data and Computational Environments

2020 · arXiv (Cornell University)

There are situations where data relevant to a machine learning problem are distributed among multiple locations that cannot share the data due to regulatory, competitiveness, or privacy reasons. For example, data present in users' cellphones, …

Scaling Neuroscience Research Using Federated Learning

2021

The amount of biomedical data continues to grow rapidly. However, the ability to analyze these data is limited due to privacy and regulatory concerns. Machine learning approaches that require data to be copied to a …