University of Cambridge > Talks.cam > Artificial Intelligence Research Group Talks (Computer Laboratory) > Gaussian Processes on Graphs via Spectral Kernel Learning

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Gaussian Processes on Graphs via Spectral Kernel Learning

Download to your calendar using vCal

If you have a question about this talk, please contact Mateja Jamnik .

Join us on Zoom

I will go over topics on regularization, RKHS , and filtering on graphs. I will then show how I applied these methods to graph signal prediction through a graph spectrum-based Gaussian process. The model is designed to capture various graph signal structures through a highly adaptive kernel that incorporates a flexible polynomial function in the graph spectral domain. I will also present a bespoke maximum likelihood learning algorithm that enforces the positivity of the polynomial to achieve interpretability of filtering on graphs.

BIO : Yin-Cong Zhi is a fourth year DPhil student with Xiaowen Dong at the Oxford Man Institute. His focus is in graph signal processing and kernel methods, and utilising these tools for predictive tasks on graphs using Gaussian processes.

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Cambridge Nutritank Wolfson Lecture Theatre, Chemistry Department Bri

Other talks

CodeScaler: Scaling Code LLM Training and Test-Time Inference via Execution-Free Reward Models Complete and Submit Project Choice Forms When is a mummy not a mummy? Andean bodies and the problem of scientific classification in Britain From lab to clinic: an introduction to translational research BSU Seminar: "Response Adaptivity Across Clinical Trials In Portfolios of Biomedical Innovations" Christmas Social Evening & Annual General Meeting
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity