Multi-Relational Graph Neural Network for Out-of-Domain Link Prediction

arXiv:2403.11292v1 Announce Type: new
Abstract: Dynamic multi-relational graphs are an expressive relational representation for data enclosing entities and relations of different types, and where relationships are allowed to vary in time. Addressing predictive tasks over such data requires the ability to find structure embeddings that capture the diversity of the relationships involved, as well as their dynamic evolution. In this work, we establish a novel class of challenging tasks for dynamic multi-relational graphs involving out-of-domain link prediction, where the relationship …

abstract arxiv cs.ai cs.lg data diversity domain dynamic embeddings graph graph neural network graphs link prediction network neural network prediction predictive relational relations relationships representation tasks type types