Li, Qinbin

I like to learn and discover new things. Being a PhD student, I can study the state-of-the-art theories in an area I like. Moreover, I can propose and try my ideas and even publish them. Research is interesting. I like to challenge myself and solve tough problems.

My main research interests lie in federated learning and differential privacy. Many machine learning algorithms are data hungry. However, in reality, data are dispersed over different organizations under the protection of privacy restrictions. Federated learning enables multiple parties to collaboratively train a machine learning model without exchanging their local data. It is a very interesting and meaningful research area. Moreover, machine learning models suffer from potential attacks, which may leak sensitive information about training data. Differential privacy can help to protect the models in a simple and effective way. These two areas have attracted many researchers.

The most existing part of my graduate journey is that my papers got accepted into top computer science conferences.