The Institute of Informatics and Telecommunications of NCSR Demokritos has an important role in the large-scale European research project, for the development of explicable machine learning for large-scale knowledge graphs, called ENEXA (Efficient Explainable Learning on Knowledge Graphs).
The project’s kick-off meeting took place in Paderborn, Germany, on 4 October 2022, on the premises of Paderborn University, where partner representatives had the chance to meet for the first time and present, in detail, their role within the project.
ENEXA is funded by the European Commission’s Horizon Europe Program and will last for 3 years. ENEXA will devise new machine learning approaches, that will maintain formal guarantees pertaining to completeness and correctness, while exploiting different representations (formal logics, embeddings and tensors) of knowledge graphs in a concurrent fashion. With the new methods, the plan is to achieve significant advances in the scalability of machine learning, especially on knowledge graphs. The key innovation of ENEXA lies in its approach to explainability. The main focus will be on devising human-centred explainability techniques, based on the concept of co-construction, where human and machine enter a conversation to co-construct human-understandable explanations. The resulting approach will be deployed in three sectors of European significance, i.e., business services, geospatial intelligence and brand marketing.
The partnership consists of six partners from five countries: coordinator Paderborn University (Germany), National Centre for Scientific Research “Demokritos” (Greece), European Union Satellite Centre (Spain), DATEV (Germany), University of Amsterdam (Netherlands) and WebLyzard Technology (Austria).