We are happy to announce that the papers “Impact of the Characteristics of Multi-Source Entity Matching Tasks on the Performance of Active Learning Methods” by Anna Primpeli and Christian Bizer and the paper “Supervised Knowledge Aggregation for Knowledge Graph Completion” by Patrick Betz, Christian ...

The paper “NuPS: A Parameter Server for Machine Learning with Non-Uniform Parameter Access” by Alexander Renz-Wieland, Rainer Gemulla, Zoi Kaoudi, and Volker Markl  has been accepted at the 2022 ACM SIGMOD International Conference on Management of Data. Abstract: Parameter servers (PSs) ...

The paper “Parallel Training of Knowledge Graph Embedding Models: A Comparison of Techniques” by Adrian Kochsiek and Rainer Gemulla has been accepted at the 2022 Proceedings of the VLDB Endowment (PVLDB). Abstract: Knowledge graph embedding (KGE) models represent the entities and relations of a ...

The paper “Efficient Learning of Discrete-Continuous Computation Graphs” by David Friede and Mathias Niepert (NEC Research Labs) has been accepted for the 35th Conference on Neural Information Processing Systems (NeurIPS 2021).

Michael Pernpeinter, PhD Student in the AI Group successfully applied for a Fulbrigth Scholarship to visit Texas A&M University and work with Prof. Guni Sharon on Governance of Autonomous Multi-Agent Systems.

Our paper “Background Knowledge in Schema Matching: Strategy vs. Data” has been accepted at the 20th International Semantic Web Conference. The paper has been co-authored by Jan Portisch, Michael Hladik, and Heiko Paulheim. In the paper, we have conducted a number of controlled experiments with ...

The paper “Winning at Any Cost – Infringing the Cartel Prohibition With Reinforcement Learning” was accepted at the 19th International Conference on Practical Applications of Agents and Multi-Agent Systems.

The paper “GraphConfRec: A Graph Neural Network-Based Conference Recommender System”, co-authored by Andreea Iana and Heiko Paulheim, has been accepted for publication at the ACM/IEEE Joint Conference on Digital Libraries. In the paper, we explore the usage of modern graph neural network based ...

Earlier this year, we introduced kgextension, the Python extension for processing knowledge graphs. With this extension, data analysts can easily link their data at hand to both public and private knowledge graphs, and add the wealth of public knowledge graphs such as Wikidata to their data ...