Skip to main navigation Skip to Content

Computer Science

University of Toronto
  • U of T Portal
  • Student Support
  • Contact
  • About
    • Why Study CS at U of T
    • Career Options
    • History of DCS
    • Giving to DCS
    • Computer Science at UofT Mississauga
    • Computer Science at UofT Scarborough
    • Contact
    • Employment Opportunities for Faculty/Lecturers
    • How to Find Us
  • Undergraduate
    • Prospective Undergraduates
    • Current Undergraduates
  • Graduate
    • Prospective Graduate students
    • Current Graduate students
  • Research
    • Research Areas
    • Partner with us
  • People
    • Faculty
    • Staff
    • In Memoriam
    • Alumni and Friends
    • Honours & Awards
    • Women in Computer Science
    • Graduate Student Society
    • Undergraduate Student Union
    • Undergraduate Artificial Intelligence Group
    • Undergraduate Theory Group
  • News & Events
    • News
    • Events
    • @DCS Update
    • Alumni
    • Donate
You are viewing: > Home > News & Events > Events > Google Talk - Machine Learning on Graphs: Jan 18
  • About
  • Undergraduate
  • Graduate
  • Research
  • People
  • News & Events

Google Talk - Machine Learning on Graphs: Jan 18

Event date: Thursday, January 18, 2018, from 9:30 AM to 10:30 AM
Location: Mechanical Engineering Building, Rm. 102

On Thursday Jan. 18, Sami Abu-El-Haija, UofT Alumni and currently at Google Research, will be at UofT to share a talk on Machine Learning on Graphs, hosted by the Department of Electrical & Computer Engineering.

Join Sami as he summarizes the field, sharing insights about some of Google's work in this area. You will learn about representing graphs in a continuous vector space, graph convolution, random walks, and how these techniques can be used for unsupervised and semi-supervised learning.

Please RSVP here

This talk is well suited to gradate students in ECE, CS, Math, etc. Students who might not be familiar with Machine Learning or Representation Learning are encouraged to join, as Sami will provide a review of the field.

Abstract: Graph-structured data is prevalent across many domains, including social networks, biological networks, and e-commerce. In these settings, one might wish to infer information missing from the graph, for example, predict user interests in a social network or predict if two proteins interact in a biological network. However, modern Machine Learning techniques, such as Deep Learning, usually operate on continuous-valued inputs (e.g. floating-point numbers) while graphs are naturally described in discrete form (e.g. nodes and edges). In this talk, the speaker will describe modern embedding techniques that project graphs onto a continuous vector space. In addition, he will describe graph convolution and how it can be used for semi-supervised node classification, where the labels are observed for only a fraction of the nodes and one wishes to recover all unobserved labels. You will hear about some of Google's work in these domains, which include learning an edge function, and combining random walks with graph convolution for semi-supervised learning. Students who might not be familiar with Machine Learning or Representation Learning are encouraged to join, as he will do a review of the field.

Biography: Sami Abu-el-haija (CompE 1T0) completed his BASc degree at the University of Toronto, from the Electrical and Computer Engineering department in 2010. He then worked for several Silicon Valley startups, before starting his graduate work at Stanford and the University of Michigan. He currently holds a position at Google Research, in the Machine Perception group, where he collaborates with various groups working on Video Understanding, Optimization, and Large-scale Graphs.

Please email utoronto-tech-students@google.com with any questions.


All rights reserved copyright Computer Science, University of Toronto | Site Map