Recent years have seen a huge increase in Machine Learning research also with a focus on Knowledge and Semantic Web. While Machine Learning techniques have always played an important role in semantic technologies, now also core challenges from the Semantic Web area are being recognized by a wider Machine Learning community. For example, one focus has been on learning knowledge graph embeddings optimized for link prediction. To this end, leveraging large knowledge bases for machine learning models is only half of the coin as machine learning is also the enabler of the semantic web in a sense that it e.g. makes the information hidden in unstructured data like text usable.
The Machine Learning track of ESWC has a long track record of covering research combining both, symbolic knowledge representations with inductive learning techniques. We invite high quality submissions that contribute in both directions or combine both: either improving knowledge representations by machine learning approaches, improving the performance of machine learning methods by exploiting knowledge representations or the direct combination of probabilistic and logic approaches.
Topics of interest include, but are not limited to, the following:
- Statistical Relational Learning for the Web of Data, Knowledge Graphs, Ontologies
- Representation Learning for the Integration of Unstructured Data with Knowledge Bases
- Machine Learning on top of Structured Data and Knowledge Graphs
- Learning of Knowledge Graph Embeddings
- Machine Learning for Knowledge Graph Construction, Completion, Refinement
- Machine Learning approaches like Deep Learning, Graph-Kernels, Tensor methods, Relational Graphical Models for the Semantic Web.
- Approximate Inductive Reasoning on Ontologies
- Machine learning for Ontology Matching, Instance Matching, Search and Retrieval
- Data Mining and Knowledge Discovery from Linked data and Ontologies
- Learning from Big Data for web-scale Knowledge Graphs