Ismail Ilkan Ceylan
My research interests are broadly in AI & machine learning with a particular focus on relational learning & reasoning, which includes a class of challenging problems that can be naturally characterised on relational structures, such as graphs, knowledge bases, or more general logical representations. 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 (e.g., deep learning, graph representation learning, probabilistic inference), knowledge representation (e.g., logical reasoning), and theoretical computer science (complexity theory, graph theory) are relevant.
Note: If you are interested in applying for a DPhil, please get in touch beforehand. It might also be helpful to have a brief look at my graph representation learning course.
The Dichotomy of Evaluating Homomorphism−Closed Queries on Probabilistic Graphs
Antoine Amarilli and İsmail İlkan Ceylan
In Logical Methods in Computer Science. Vol. 18/1. 2022.
Shortest Path Networks for Graph Property Prediction
Ralph Abboud‚ Radoslav Dimitrov and İsmail İlkan Ceylan
In Proceedings of the First Learning on Graphs Conference (LoG). 2022.
Query Answer Explanations under Existential Rules
İsmail İlkan Ceylan‚ Thomas Lukasiewicz‚ Enrico Malizia and Andrius Vaicenavicius
In Giuseppe Amato‚ Valentina Bartalesi‚ Devis Bianchini‚ Claudio Gennaro and Riccardo Torlone, editors, Proceedings of the 30th Italian Symposium on Advanced Database Systems‚ SEBD 2022‚ Tirrenia (PI)‚ Italy‚ June 19−22‚ 2022. Vol. 3194 of CEUR Workshop Proceedings. Pages 481–488. CEUR−WS.org. 2022.