MACHINE LEARNING IN NETWORKS

June 29-July 1, 2020

MACHINE LEARNING IN NETWORKS

Track 2

Session 3

Course Description

This course provides an introduction to modern machine learning techniques apt to reveal insights on the social, technological, and natural worlds, by means of studying their underlying network structure and interconnections. The course focuses on basic graph representation learning concepts, deep learning for graphs, exploring graph neural networks, their strengths, applications, limitations, and their connection to traditional network embedding methods.

Instructors

Bruno Ribeiro

Purdue University

Jure Leskovec

Stanford University

Student preparation

The course will be a mix of conceptual and technical content. The computational portion of the course will mainly rely on in-class demonstrations, as well as exercises using Python and the Pytorch deep learning library.

Students should be familiar with:
•Basic network terminology
•Basic linear algebra
•Basic probability theory
•Basic programming skills in Python

About the instructors

Bruno Ribeiro

Bruno Ribeiro is an Assistant Professor in the Department of Computer Science at Purdue University. Previously, he received his PhD from the University of Massachusetts Amherst and spent two years as a postdoctoral fellow at Carnegie Mellon University. He is the recipient of a 2020 NSF CAREER award and a 2016 ACM SIGMETRICS best paper award. Ribeiro’s research interests are in machine learning and data mining, with a focus on modeling and sampling relational and temporal data.

Jure Leskovec

Jure Leskovec is Associate Professor of Computer Science at Stanford University, Chief Scientist at Pinterest, and investigator at Chan Zuckerberg Biohub. He was the co-founder of a machine learning startup Kosei, which was later acquired by Pinterest. His research focuses on machine learning and data mining large social, information, and biological networks. Computation over massive data is at the heart of his research and has applications in computer science, social sciences, marketing, and biomedicine. This research has won several awards including a Lagrange Prize, Microsoft Research Faculty Fellowship, the Alfred P. Sloan Fellowship, and numerous best paper and test of time awards. Leskovec received his bachelor's degree in computer science from University of Ljubljana, Slovenia and his PhD in machine learning from Carnegie Mellon University. He performed his postdoctoral training at Cornell University.

© 2019. All rights reserved.