Currently, Deep Learning (DL) components within a Case-Based Reasoning (CBR) application often lack the comprehensive integration of available domain knowledge. The trend within machine learning towards so-called Informed machine learning can help to overcome this limitation. In this paper, we therefore investigate the potential of integrating domain knowledge into Graph Neural Networks (GNNs) that are used for similarity assessment between semantic graphs within process-oriented CBR applications. We integrate knowledge in two ways: First, a special data representation and processing method is used that encodes structural knowledge about the semantic annotations of each graph node and edge. Second, the message-passing component of the GNNs is constrained by knowledge on legal node mappings. The evaluation examines the quality and training time of the extended GNNs, compared to the stock models. The results show that both extensions are capable of providing better quality, shorter training times, or in some configurations both advantages at once.

This paper presents a novel approach to retrieval in process-oriented case-based reasoning (POCBR) which considers the adaptability of workflows cases during the retrieval phase. A novel concept of adaptability in POCBR is proposed, which assesses the potential similarity increase of a case which can be gained by adaptation. The adaptability of a case is learned from the case base in an off-line pre-processing phase prior to the retrieval. The proposed approach is generic as it can be used in combination with different adaptation methods. An empirical evaluation in the domain of cooking workflows demonstrates the benefit of the approach.