Published multiple papers, including 'Representation learning in multiplex graphs: Where and how to fuse information?' (February 2024) and 'Graph-level representations using ensemble-based readout functions' (May 2023, ICCS 2023). His work has garnered over 100 citations.
Research Experience
AI Frameworks Engineer at Intel Corporation and Assistant Professor at Wrocław University of Science and Technology.
Education
PhD in Computer Science (Machine Learning), 2019-2023, Wrocław University of Science and Technology; MSc in Computer Science (Data Science specialization), 2018-2019, Wrocław University of Science and Technology; BEng in Computer Science, 2014-2018, Wrocław University of Science and Technology.
Background
A graph machine learning specialist with over 4 years of industrial experience. His research expertise centers on graph representation learning in terms of unsupervised and self-supervised learning. He has authored both conference and journal articles, introducing pioneering methods such as GBT, AttrE2vec, and FILDNE. Proficient in Python, he is a well-rounded practitioner skilled in full-stack machine learning development, including DevOps/MLOps, model implementation, and evaluation.
Miscellany
Interests include Graph Machine Learning, Representation Learning, Unsupervised Learning, and Self-supervised Learning.