Ismail Ilkan Ceylan

Ismail Ilkan Ceylan

Departmental Lecturer

College Lecturer, Hertford College

E: ismail.ceylan at cs.ox.ac.uk

Wolfson Building, Parks Road, Oxford OX1 3QD

Themes:

• Artificial Intelligence and Machine Learning
• Algorithms and Complexity Theory
• Data and Knowledge

Completed Projects:

• RealPDBs

Interests

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.

Selected Publications

View AllManage publications

• 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.

  Details about The Dichotomy of Evaluating Homomorphism−Closed Queries on Probabilistic Graphs | BibTeX data for The Dichotomy of Evaluating Homomorphism−Closed Queries on Probabilistic Graphs | Link to The Dichotomy of Evaluating Homomorphism−Closed Queries on Probabilistic Graphs

• Temporal Knowledge Graph Completion using Box Embeddings

  Johannes Messner‚ Ralph Abboud and İsmail İlkan Ceylan

  In Proceedings of the 36th AAAI Conference on Artificial Intelligence‚ AAAI 2022‚ Vancouver‚ BC‚ Canada. AAAI Press. 2022.

  Details about Temporal Knowledge Graph Completion using Box Embeddings | BibTeX data for Temporal Knowledge Graph Completion using Box Embeddings | Link to Temporal Knowledge Graph Completion using Box Embeddings

• Equivariant Quantum Graph Circuits

  Peter Mérnyei‚ Konstantinos Meichanetzidis and İsmail İlkan Ceylan

  In Proceedings of the 39th International Conference on Machine Learning‚ ICML 2022‚ Baltimore‚ Maryland‚ USA. 2022.

  Details about Equivariant Quantum Graph Circuits | BibTeX data for Equivariant Quantum Graph Circuits | Download (pdf) of Equivariant Quantum Graph Circuits

Activities

• Deep Learning
• Knowledge Representation and Reasoning

Current Students

Past Student