Business Entity Matching with Siamese Graph Convolutional Networks


  • Evgeny Krivosheev IBM Research - Zurich, Switzerland University of Trento, Italy
  • Mattia Atzeni IBM Research - Zurich, Switzerland EPFL, Switzerland
  • Katsiaryna Mirylenka IBM Research - Zurich, Switzerland
  • Paolo Scotton IBM Research - Zurich, Switzerland
  • Christoph Miksovic IBM Research - Zurich, Switzerland
  • Anton Zorin IBM Research - Zurich, Switzerland


Data Integration, Business Entity Matching, Graph Convolutional Networks


Data integration has been studied extensively for decades and approached from different angles. However, this domain still remains largely rule-driven and lacks universal automation. Recent developments in machine learning and in particular deep learning have opened the way to more general and efficient solutions to data-integration tasks. In this paper, we demonstrate an approach that allows modeling and integrating entities by leveraging their relations and contextual information. This is achieved by combining siamese and graph neural networks to effectively propagate information between connected entities and support high scalability. We evaluated our approach on the task of integrating data about business entities, demonstrating that it outperforms both traditional rule-based systems and other deep learning approaches.




How to Cite

Krivosheev, E., Atzeni, M., Mirylenka, K., Scotton, P., Miksovic, C., & Zorin, A. (2021). Business Entity Matching with Siamese Graph Convolutional Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 16054-16056. Retrieved from