2022/08/30 by Harry Shomer, Wei Jin, Shomer, Harry +8 · 6 citations
Computer Science · Decision Sciences · Mathematics · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Artificial intelligence #Base (topology) #Computer science #Data Quality and Management #Data science #FOS: Computer and information sciences #Focus (optics) #Graph #Information retrieval #Knowledge base #Knowledge graph #Machine Learning (cs.LG) #Mathematics #Perspective (graphical) #Relational database #Relational model #Statistical relational learning #Theoretical computer science #Topic Modeling #cs.AI #cs.LG
paper · pdf · doi:10.48550/arxiv.2208.14322
published in arXiv (Cornell University) (Cornell University)
arxiv created 2022/08/30 · openalex publication_date 2022/08/30 · arxiv updated 2022/08/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Knowledge graphs (KGs) have gained prominence for their ability to learn representations for uni-relational facts. Recently, research has focused on modeling hyper-relational facts, which move beyond the restriction of uni-relational facts and allow us to represent more complex and real-world information. However, existing approaches for learning representations on hyper-relational KGs majorly focus on enhancing the communication from qualifiers to base triples while overlooking the flow of information from base triple to qualifiers. This can lead to suboptimal qualifier representations, especially when a large amount of qualifiers are presented. It motivates us to design a framework that utilizes multiple aggregators to learn representations for hyper-relational facts: one from the perspective of the base triple and the other one from the perspective of the qualifiers. Experiments demonstrate the effectiveness of our framework for hyper-relational knowledge graph completion across multiple datasets. Furthermore, we conduct an ablation study that validates the importance of the various components in our framework. The code to reproduce our results can be found at \urlhttps://github.com/HarryShomer/QUAD.