A unified Link Prediction architecture applied on a novel Heterogenous Knowledge Base

Link Prediction (LP) aims at addressing incompleteness of Knowledge Graph (KG). The goal LP is to capture the distribution entities and relations present in a KG utilise these predict probability missing information. State-of-the-art approaches rely on latent feature models for this purpose. research focus has predominantly been application triple based datasets (e.g. Freebase, YAGO). However, with growing adoption KGs, it common see more heterogeneous property graphs being used, examples properties are temporal weight data. contributions following work two fold. First, we introduce novel framework which first provide support model Bases (KBs). Second, KB — Refinitiv Graph, produce dataset capabilities examined.