SCS Faculty Candidate - Mai Elkady

— 3:00pm

Location:
In Person and Virtual - ET - Newell-Simon 4305 and Zoom

Speaker:
MAI ELKADY , Ph.D. Candidate, Department of Computer Science, Purdue University
https://www.linkedin.com/in/mai-elkady

An Introduction to Graph Neural Networks

Graphs are a natural representation of complex systems, from social networks to molecular structures. Working directly on graphs allows us to capture relational information that would be difficult to encode otherwise. Graph Neural Networks (GNN) are a class of models that extends deep learning to non-Euclidean data, making learning directly on graphs feasible. In this talk, I will discuss the motivation behind using graphs in machine learning, then walk through the key building blocks of GNNs—message passing, aggregation, and update functions. I will present examples of recent GNN architectures and highlight common GNN tasks including node classification, link prediction, and graph classification. 

— 

Mai Elkady is a Ph.D. candidate at Purdue University specializing in machine learning with a focus on discrete generative models, and graph learning. During her Ph.D. Mai had an extensive teaching experience, serving as a teaching assistant for multiple undergraduate courses and as an instructor of record for a programming course through Purdue’s Graduate Teaching Fellowship program. Her commitment to education earned her the Purdue Graduate Teaching Award in Spring 2020. In addition to her academic work, Mai interned at Microsoft and Block Inc., contributing to both applied and research projects in Natural Language Processing (NLP), heterogeneous graph learning, and scalable Graph Neural Network architectures. 

Joint Machine Learning Department and Computer Science Department
In Person and Zoom Participation.  See announcement. 

→ Attendance at this talk is restricted to members of the SCS community and relevant CMU stakeholders.

Add event to Google
Add event to iCal