Distributed Representations of Entities in Open-World Knowledge Graphs

arXiv:2010.08114v2 Announce Type: replace
Abstract: Graph neural network (GNN)-based methods have demonstrated remarkable performance in various knowledge graph (KG) tasks. However, most existing approaches rely on observing all entities during training, posing a challenge in real-world knowledge graphs where new entities emerge frequently. To address this limitation, we introduce Decentralized Attention Network (DAN). DAN leverages neighbor context as the query vector to score the neighbors of an entity, thereby distributing the entity semantics only among its neighbor embeddings. To effectively …

abstract arxiv attention challenge cs.ai cs.cl cs.lg decentralized distributed gnn graph graph neural network graphs however knowledge knowledge graph knowledge graphs network neural network open-world performance tasks training type world