skip to primary navigationskip to content

Talk on Representation Learning on Graphs

last modified Mar 18, 2019 12:33 PM

Jure Leskovec - Associate Professor of Computer Science at Stanford University, Chief Scientist at Pinterest, and investigator at Chan Zuckerberg Biohub
Wednesday 20 March 2019, 16:15-17:00
Lecture Theatre 2, Computer Laboratory, Cambridge University

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.