Abstract

Knowledge graphs are freely aggregated, published, and edited in the Web of data, and thus may overlap. Hence, a key task resides in aligning (or matching) their content. This task encompasses the identification, within an aggregated knowledge graph, of nodes that are equivalent, more specific, or weakly related. In this article, we propose to match nodes within a knowledge graph by (i) learning node embeddings with Graph Convolutional Networks such that similar nodes have low distances in the embedding space, and (ii) clustering nodes based on their embeddings, in order to suggest alignment relations between nodes of a same cluster. We conducted experiments with this approach on the real world application of aligning knowledge in the field of pharmacogenomics, which motivated our study. We particularly investigated the interplay between domain knowledge and GCN models with the two following focuses. First, we applied inference rules associated with domain knowledge, independently or combined, before learning node embeddings, and we measured the improvements in matching results. Second, while our GCN model is agnostic to the exact alignment relations (e.g., equivalence, weak similarity), we observed that distances in the embedding space are coherent with the “strength” of these different relations (e.g., smaller distances for equivalences), letting us considering clustering and distances in the embedding space as a means to suggest alignment relations in our case study.

Highlights

  • The Semantic Web [3] offers tools and standards that facilitate the construction of knowledge graphs [17] that may aggregate data and elements of knowledge of various provenances

  • We proposed to match entities of a knowledge graph by learning node embeddings with Graph Convolutional Networks (GCNs) and clustering nodes based on their embeddings

  • We investigated the interplay between formal semantics associated with knowledge graphs and GCN models

Read more

Summary

Introduction

The Semantic Web [3] offers tools and standards that facilitate the construction of knowledge graphs [17] that may aggregate data and elements of knowledge of various provenances. P. Monnin et al / Discovering alignment relations with Graph Convolutional Networks: A biomedical case study of knowledge allows access to a larger extent of the available knowledge, which is beneficial to many applications, such as fact-checking or query answering. Monnin et al / Discovering alignment relations with Graph Convolutional Networks: A biomedical case study of knowledge allows access to a larger extent of the available knowledge, which is beneficial to many applications, such as fact-checking or query answering For this conjoint use to be possible, one crucial task lies in matching units across knowledge graphs or within an aggregated knowledge graph, i.e., finding alignments or correspondences between nodes, edges, or subgraphs. Different alignment relations may hold between units: some may indicate that two units are equivalent, weakly related, or that one is more specific than the other

Objectives
Discussion
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.