Abstract
The RDF2vec method for creating node embeddings on knowledge graphs is based on word2vec, which, in turn, is agnostic towards the position of context words. In this paper, we argue that this might be a shortcoming when training RDF2vec, and show that using a word2vec variant which respects order yields considerable performance gains especially on tasks where entities of different classes are involved.
Related Papers
SMART: Relation-Aware Learning of Geometric Representations for Knowledge Graphs2025-07-17Topic Modeling and Link-Prediction for Material Property Discovery2025-07-08Graph Collaborative Attention Network for Link Prediction in Knowledge Graphs2025-07-05Context-Driven Knowledge Graph Completion with Semantic-Aware Relational Message Passing2025-06-29Active Inference AI Systems for Scientific Discovery2025-06-26Enhancing LLM Tool Use with High-quality Instruction Data from Knowledge Graph2025-06-26Generating Reliable Adverse event Profiles for Health through Automated Integrated Data (GRAPH-AID): A Semi-Automated Ontology Building Approach2025-06-25Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs2025-06-24