Graph Transformations

In this episode, Adam Machowczyk, a PhD student at the University of Leicester, specializes in graph rewriting and its intersection with machine learning, particularly Graph Neural Networks. Adam explains how graph rewriting provides a formalized method to modify graphs using rule-based transformations, allowing for tasks like graph completion, attribute prediction, and structural evolution. Bridging the worlds of graph rewriting and machine learning, Adam's work aspire to open new possibilities for creating adaptive, scalable models capable of solving challenges that traditional methods struggle with, such as handling heterogeneous graphs or incorporating incremental updates efficiently. Real-life applications discussed include using graph transformations to improve recommender systems in social networks, molecular research in chemistry, and enhancing IoT network analysis.

Guest

Adam Machowczyk: "Adam completed his BSc at De Montfort University in 2021 with first class in Computing. Following this achievement, he moved to The University of Leicester for his MSc in Cloud Computing, which he completed in 2022. His MSc project became the backbone of his PhD application and was awarded the Best Technical MSc project award. He was also honored with the Best Student in Informatics award in November 2022. In his research, he is actively trying to find a way to apply Graph Rewriting to Graph Neural Networks. He is funded by The University, working as a GTA, under the supervision of Prof. Reiko Heckel."