University of Cambridge > Talks.cam > Women@CL Events > How does the classical TE problem Enter the Federated Learning Era step by step?

How does the classical TE problem Enter the Federated Learning Era step by step?

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Kayla-Jade Butkow.

Abstract: With the rise of edge networks, regional terminal data has been explosively generated in recent years, so how to solve large-scale cross-domain data transmission is becoming a more and more widely concerned topic. In this talk, I’ll first introduce our BDS +, a fast data duplication system by exploring bottleneck disjoint overlay paths. On this basis, I’ll continue to explore link failure scenario and data privacy issues step by step, and ending by introducing federated learning into traditional traffic engineering and resource scheduling problem.

Zoom link: To be released on the day of the talk.

Bio: Dr. Yuchao Zhang is an Associate Professor from Beijing University of Posts and Telecommunications, China, where she is the Director of Network and Software Communication Centre. She is currently a Visiting Scholar in Cambridge University and also a Visiting Research Associate in Wolfson College. Her research interests include Data-driven Network, Edge Computing, Federated Learning and BlockChain, and she has a number of National and International projects in related fields. You can know more about her here:http://yuchaozhang.weebly.com/

This talk is part of the Women@CL Events series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2022 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity