University of Cambridge > Talks.cam > Computer Laboratory Wednesday Seminars > Representation Learning on Graphs

Representation Learning on Graphs

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

  • UserJure Leskovec - Associate Professor of Computer Science at Stanford University, Chief Scientist at Pinterest, and investigator at Chan Zuckerberg Biohub
  • ClockWednesday 20 March 2019, 16:15-17:00
  • HouseLecture Theatre 2, Computer Laboratory.

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

Machine learning on graphs is an important and ubiquitous task with applications ranging from drug design to friendship recommendation in social networks. The primary challenge in this domain is finding a way to represent, or encode, graph structure so that it can be easily exploited by machine learning models. However, traditionally machine learning approaches relied on user-defined heuristics to extract features encoding structural information about a graph. In this talk I will discuss methods that automatically learn to encode graph structure into low-dimensional embeddings, using techniques based on deep learning and nonlinear dimensionality reduction. I will provide a conceptual review of key advancements in this area of representation learning on graphs, including random-walk based algorithms, and graph convolutional networks. We will discuss applications to web-scale recommender systems, healthcare and knowledge representation and reasoning.

The slides from the talk: http://i.stanford.edu/~jure/pub/talks2/graphsage_gin-cambridge-mar19.pdf

The talk was not recorded due to technical issues.

This talk is part of the Computer Laboratory Wednesday Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity