University of Cambridge > Talks.cam > Machine Learning @ CUED > Structured deep models: Deep learning on graphs and beyond

  Browse A-Z

Log in

University Account External (via Google)

๐Ÿ” Log In

Information on

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

โ„น๏ธ Information

Structured deep models: Deep learning on graphs and beyond

Download to your calendar using vCal

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

In the recent years there has been an increasing number of success stories in applying deep learning techniques to graph-structured data. The workhorse in this emerging field is the graph neural network: a message passing algorithm parameterized by neural networks, trained via backpropagation. Variants of graph neural networks now define the state of the art in many classical graph or network problems, such as node classification, graph classification, and link prediction.

In this talk, I will give an overview of structured deep models that employ graph neural networks as a key component and discuss trade-offs for a few popular model variants such as graph convolutional networks (GCNs) [1] and graph attention networks (GATs) [2]. I will further introduce two emerging research directions: learning deep generative models of graphs and inference of latent graph structure. Structured deep models are ideal candidates for these areas and hold promise for applications such as chemical synthesis, program induction, and modeling of interacting physical and multi-agent systems.

[1] Kipf & Welling, Semi-supervised classification with graph convolutional networks, ICLR 2017 [2] Veliฤkoviฤ‡ et al., Graph attention networks, ICLR 2018

This talk is part of the Machine Learning @ CUED series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Goldsmith's 2 & https://us06web.zoom.us/j/81688365420?pwd=b3RpdHgxNVhWbWQrbXluMUxYNWVtQT09 Meeting ID: 816 8836 5420 Passcode: 047859 Conduct thorough background research prior to anything else Part II room, Department of Genetics. Please use the entrance by the Part II room and tea room underneath the external fire escape. Main entrance is not connected to Part II room due to refurbishment.

Other talks

Title and abstract tba Title to be confirmed From Surrogate Solvers to PINNs and Beyond Classical Methods Discovery Investigations: Science, Empire and the Making of the British South Atlantic Title to be confirmed Beyond Hubble: Studying the Earliest Galaxies with the James Webb Space Telescope
 

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