Treat Different Negatives Differently: Enriching Loss Functions with Domain and Range Constraints for Link Prediction

arXiv:2303.00286v4 Announce Type: replace
Abstract: Knowledge graph embedding models (KGEMs) are used for various tasks related to knowledge graphs (KGs), including link prediction. They are trained with loss functions that consider batches of true and false triples. However, different kinds of false triples exist and recent works suggest that they should not be valued equally, leading to specific negative sampling procedures. In line with this recent assumption, we posit that negative triples that are semantically valid w.r.t. signatures of relations …

abstract arxiv constraints cs.ai cs.lg domain embedding embedding models false functions graph graphs however knowledge knowledge graph knowledge graphs link prediction loss prediction tasks true type