Towards Foundation Models for Knowledge Graph Reasoning

arXiv:2310.04562v2 Announce Type: replace
Abstract: Foundation models in language and vision have the ability to run inference on any textual and visual inputs thanks to the transferable representations such as a vocabulary of tokens in language. Knowledge graphs (KGs) have different entity and relation vocabularies that generally do not overlap. The key challenge of designing foundation models on KGs is to learn such transferable representations that enable inference on any graph with arbitrary entity and relation vocabularies. In this work, …

abstract arxiv challenge cs.ai cs.cl foundation graph graphs inference inputs key knowledge knowledge graph knowledge graphs language reasoning textual the key tokens type vision visual