DATA TALK "Deep Multi-view Clustering"

Michael Kampffmeyer - Associate Professor and Head of the Machine Learning Group at UiT The Arctic University of Norway
Data Science

Date: -
Location: Eurecom

Abstract: Finding underlying group structures in data via clustering is a fundamental problem in Machine Learning and finds applications in a vast area of domains. Traditional clustering approaches, however, require hand-crafted feature engineering, scale poorly to large datasets and high dimensions, and/or only allow for linear clustering. Inspired by the large improvements that deep learning-based models have brought to a variety of supervised tasks, there has been a growing interest in deep clustering approaches. This talk outlines our recent line of work on deep clustering with a particular focus on the multi-view settings, where data is observed through multiple views or by multiple modalities. Further, it discusses the role of self-supervised learning and contrastive alignment within this context. Bio: Michael Kampffmeyer is an Associate Professor and Head of the Machine Learning Group at UiT The Arctic University of Norway. He is also a Senior Research Scientist II at the Norwegian Computing Center in Oslo. His research interests include medical image analysis, explainable AI, and learning from limited labels (e.g. clustering, few/zero-shot learning, domain adaptation and self-supervised learning). Kampffmeyer received his PhD degree from UiT in 2018. He has had long-term research stays in the Machine Learning Department at Carnegie Mellon University and the Berlin Center for Machine Learning at the Technical University of Berlin. He is a general chair of the annual Northern Lights Deep Learning Conference, NLDL. For more details visit https://sites.google.com/view/michaelkampffmeyer/.