Adam Machowczyk

I am a PhD candidate in Computer Science at the University of Leicester, supervised by Professor Reiko Heckel. My PhD develops benchmark-first frameworks for graph-to-graph learning. My research focuses on graph machine learning, Deep Graph Transformation, Graph Neural Networks, benchmarking, and empirical model evaluation. I am interested in how graph transformation tasks should be defined, how model architectures should be compared, and how evaluation protocols can be made more reproducible across synthetic and real-world graph datasets.

My research focuses on graph machine learning, Deep Graph Transformation, Graph Neural Networks, benchmarking, and empirical model evaluation. I am interested in how graph transformation tasks should be defined, how model architectures should be compared, and how evaluation protocols can be made more reproducible across synthetic and real-world graph datasets.

Key Research Interests:

• Graph transformation learning: defining and evaluating graph-to-graph learning tasks.
• Benchmarking and reproducibility: designing shared experimental conditions for comparing model architectures.
• Graph Neural Networks and Graph Rewriting: studying how graph-structured learning systems can be made easier to specify, compare, and understand.
• Research software: building experimental pipelines for synthetic graph-computation tasks and real-world graph datasets.

Machowczyk, A., Heckel, R. (2026). Benchmark First: Defining Tasks for Graph Transformation Learning. In: Archibald, B., Semeráth, O. (eds) Graph Transformation. ICGT 2026. Lecture Notes in Computer Science, vol 16624. Springer, Cham. https://doi.org/10.1007/978-3-032-29730-3_13

Adam Machowczyk and Reiko Heckel (2025). Benchmarks for Graph Transformation Problems. Graph Computation Models 2025. Extended abstract; featured in GCM Session 3: Lightning Talks & Panel Discussion: Graph Transformation and AI. Non-archival presentation.

Adam Machowczyk and Reiko Heckel (2024). Towards Graph-to-Graph Transformation Networks. Graph Computation Models 2024. Available online at the workshop page, in the Electronic Proceedings tab. Accessed: 25/07/2024.

Reiko Heckel and Adam Machowczyk (2024). From Message Passing to Actor Graph Neural Networks. Graph Computation Models 2024. Available online at the workshop page, in the Electronic Proceedings tab. Accessed: 25/07/2024.

Machowczyk, A., Heckel, R. (2023). Graph Rewriting for Graph Neural Networks. In: Fernández, M., Poskitt, C.M. (eds) Graph Transformation. ICGT 2023. Lecture Notes in Computer Science, vol 13961. Springer, Cham. https://doi.org/10.1007/978-3-031-36709-0_16. Nominated for the best paper award.

CO4217-CO7217 Agile Cloud Automation (2022/23–2025/26)

CO2101 Operating Systems and Networking (2022/23–2025/26) 

CO1108 Foundations of Computation (2022/23–2025/26)

CO7214 Service-Oriented Architectures (2022/23–2025/26)

CO4225-CO7225 Data-Driven Intelligent Service Design (2023/24–2024/25)

CO7093 Big Data and Predictive Analytics (2022/23)

ICGT 2026: First author, reviewer.

IEEE Transactions on Human-Machine Systems 2026: Reviewer.

GCM Workshop 2026: Reviewer.

Leicester Learning and Teaching Conference 2026: Co-author.

GCM Workshop 2025: First author.

Leicester Doctoral College Research Conference 2025: Session chair.

Workshop on Graph Computation Models (GCM) 2024: First author, co-author, presenter and session co-chair.

ICGT 2024: Reviewer.

STAF Conferences 2023: Digital Communications Chair.

16th International Conference on Graph Transformation (ICGT 2023): First author, nominated for the best paper award.

Associate Fellow of the Higher Education Academy, AFHEA — 2026.

Certified Carbon Literate — 2024.

Microsoft Certified: Azure AI Fundamentals — 2023.