GeoRDF2Vec Learning Location-Aware Entity Representations in Knowledge Graphs Many knowledge graphs contain a substantial number of spatial entities, such as cities, buildings, and natural landmarks. For many of these entities, exact geometries are stored within the knowledge g...

Quite a few #KnowledgeGraphs contain geospatial entities🌍GeoRDF2vec is an extension of the #RDF2vec #embedding method that exploits geospatial information for learning better entity representations. Check it out here: arxiv.org/abs/2504.17099 #eswc2025