Google Seminar: Machine Learning on Graphs
Talk Title: Machine Learning on Graphs: Embedding, Random Walks, and Graph Convolution.
Speaker: Sami Abu-el-haija, Software Engineer, Google Research

When: Thursday, January 18, 2018 from 9:30 AM - 11:00 AM
Where: University of Toronto, MC 102

[Talk 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 edge).

In this talk, Sami 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. In this talk, he will brief 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 Sami will cover a review of the field.

[Talk Outline]

Background:
- What is a Graph?
- Machine Learning Applications on Graphs

Graph Embeddings:
- Review: Laplacian methods, Random Walks
- Structure-preserving Probabilistic Objective
- Edge Representation
- Context Distributions

Graph Convolution:
- Review: Derivation, Approximations, Graph ConvNets
- Graph Convolution on Random Walks

----------------------
[IMPORTANT] By completing this form, you are not applying for a role at Google. If you would like to apply, please see opportunities at google.com/students.

Google's use of this data is governed by our privacy policy found at google.com/about/careers/privacy/

Will you attend this event? *
Would you like to be contacted about future Google events and opportunities? *
First Name *
Your answer
Last Name *
Your answer
Primary Email *
Please submit just one. If you apply for opportunities at Google, please use the same email address.
Your answer
Phone Number
Your answer
University *
Please use full school name, not abbreviation
Required
Current Occupation *
If you are a professional, please enter your job title in "Other"
Major / Field of study *
Choose the closest match
Current degree you are pursuing *
Graduation Year *
Graduation Month *
Link to resume or CV
Please be sure to include a link to your resume if you're interested in opportunities with Google. If uploaded through Google Docs, please be sure to grant us permission to view the doc.
Your answer
Link to website
e.g. GitHub
Your answer
LinkedIn
Your answer
Please let us know if you are a member of any of the following engineering organizations or have received any of the following scholarships or awards. Choose all that apply.
If you've participated in another type of group or received another type of recognition (e.g. school or department specific scholarship, fellowship, student group, etc.) that isn't listed, please let us know in the additional box.
Special accommodations for event
Google is a disability inclusive employer. Please let us know if you require any special accommodations to attend.
Your answer
Comments or Questions
Your answer
Submit
Never submit passwords through Google Forms.
This form was created inside of Google.com. Google - Privacy & Terms - About Google