Ismail Ilkan Ceylan
Ismail Ilkan Ceylan
Wolfson Building, Parks Road, Oxford OX1 3QD
Themes:
- Artificial Intelligence and Machine Learning
- Algorithms and Complexity Theory
- Data, Knowledge and Action
Completed Projects:
Interests
My research interests are broadly in AI & machine learning with a particular focus on graph machine learning, which includes a class of challenging problems that can be naturally characterized using relational structures. The goal is to more efficiently and reliably learn from relational patterns and reason over them. This is a highly interactive field, where techniques from machine learning (e.g., deep learning, graph representation learning, probabilistic methods), knowledge representation (e.g., logical reasoning), and theoretical computer science (complexity theory, graph theory) are relevant. These methods are applied in a wide range of domains, ranging from systems in life-sciences (e.g., physical, chemical, and biological systems) to social networks.
Note: If you are interested in applying for a DPhil, it might be helpful to have a brief look at my graph representation learning course.
Selected Publications
-
Link prediction with relational hypergraphs
Xingyue Huang‚ Miguel Romero Orth‚ Pablo Barceló‚ Michael M Bronstein and İsmail İlkan Ceylan
In TMLR. 2025.
Details about Link prediction with relational hypergraphs | BibTeX data for Link prediction with relational hypergraphs
-
How Expressive are Knowledge Graph Foundation Models?
Xingyue Huang‚ Pablo Barceló‚ Michael M. Bronstein‚ İsmail İlkan Ceylan‚ Mikhail Galkin‚ Juan L Reutter and Miguel Romero Orth
In Proceedings of Fourty−second International Conference on Machine Learning (ICML). 2025.
Details about How Expressive are Knowledge Graph Foundation Models? | BibTeX data for How Expressive are Knowledge Graph Foundation Models?
-
Homomorphism Counts as Structural Encodings for Graph Learning
Linus Bao‚ Emily Jin‚ Michael Bronstein‚ İsmail İlkan Ceylan and Matthias Lanzinger
In Proceedings of the Thirteeneth International Conference on Learning Representations (ICLR). 2025.
Details about Homomorphism Counts as Structural Encodings for Graph Learning | BibTeX data for Homomorphism Counts as Structural Encodings for Graph Learning