Zero-Shot Relational Learning for Multimodal Knowledge Graphs

arXiv:2404.06220v1 Announce Type: new
Abstract: Relational learning is an essential task in the domain of knowledge representation, particularly in knowledge graph completion (KGC).While relational learning in traditional single-modal settings has been extensively studied, exploring it within a multimodal KGC context presents distinct challenges and opportunities. One of the major challenges is inference on newly discovered relations without any associated training data. This zero-shot relational learning scenario poses unique requirements for multimodal KGC, i.e., utilizing multimodality to facilitate relational learning. However, …

abstract arxiv challenges context cs.lg cs.mm domain graph graphs inference knowledge knowledge graph knowledge graphs major modal multimodal opportunities relational representation type zero-shot