CAIML Seminar with Ismail Ceylan will take place on October 24, 2024.

Abstract

This talk will present the core methodologies and techniques for deep learning with graph-structured data along with some recent advances and open problems. We will start by answering questions such as “why learning representations of graphs are useful?” firmly linking learned graph representations to various application domains. We will then move on to the question of “what are the common principles behind existing (successful) graph learning architectures?” which will be answered staring from first principles. We will then discuss some existing challenges and how they are addressed in our recent works (and how they open more avenues for future work).

About the Speaker

Ismail Ilkan Ceylan obtained his PhD at TU Dresden, Germany, with this thesis entitled “Query answering over probabilistic data and knowledge bases” which was awarded the Beth Dissertation Prize. Ismail is currently working as a lecturer at the Department of Computer Science, University of Oxford. Previously, he was working as a postdoctoral researcher at the University Oxford. Ismail’s research interests are broadly in AI and machine learning with a particular focus on relational learning and reasoning. The goal is being able to more efficiently and reliably learn from relational patterns and reason over them. This is a highly interactive field, where techniques from machine learning, knowledge representation, and theoretical computer science are relevant.