Recent advances in Concept Learning
- Lamarr
Abstract: This talk discusses the Lamarr project WHALE, which aims to advance neuro-symbolic concept learning at web scale. We begin with an overview of foundational principles in concept learning. Then, we examine limitations of existing systems—such as scalability challenges, adaptability issues, and vulnerability to noisy data. To address these gaps, we introduce innovations that improve runtime efficiency and accuracy by integrating tensor-based models and embedding techniques. These methods bridge neural flexibility and symbolic precision, enabling robust performance even with imperfect data. WHALE represents a significant step toward scalable, reliable concept learning at Web scale.
Prof. Axel-Cyrille Ngonga Ngomo
Bio: Prof. Dr. Ngonga studied Computer Science and Physics at Leipzig University. In his doctoral studies, he developed unsupervised and weakly supervised methods for the extraction of ontologies from large text corpora. His work was granted the best student paper award at CICLing 2008. His habilitation focused on machine learning and rapid execution approaches for data integration. He then led the Agile Knowledge Engineering and Semantic Web group at Leipzig University, where he performed research on various topics related to the lifecycle of knowledge graphs. Since 2017, he is a full professor (W3) of Data Science at Paderborn University, where he is also the director of the Joint Artificial Intelligence Institute and of the Computer Science Computing Facility. He has received over 30 international awards-including 6 best paper awards and a Next Einstein Fellowship-for works on knowledge extraction, fact checking, benchmarking, storage, and machine learning on knowledge graphs. Amongst others, he is one of the first two Lamarr fellows. Prof. Ngonga is currently a PI in over 15 national and international research projects and the coordinator of the doctoral training network LEMUR on learning with multiple representations.