Sphere: Expressive And Interpretable Knowledge Graph Embedding For Set Retrieval

Abstract

Knowledge graphs (KGs), which store an extensive number of relational facts (head, relation, tail), serve various applications. While many downstream tasks highly rely on the expressive modeling and predictive embedding of KGs, most of the current KG representation learning methods, where each entity is embedded as a vector in the Euclidean space and each relation is embedded as a transformation, follow an entity ranking protocol. On one hand, such an embedding design cannot capture many-to-many relations. On the other hand, in many retrieval cases, the users wish to get an exact set of answers without any ranking, especially when the results are expected to be precise, e.g., which genes cause an illness. Such scenarios are commonly referred to as "set retrieval". This work presents a pioneering study on the KG set retrieval problem. We show that the set retrieval highly depends on expressive modeling of many-to-many relations, and propose a new KG embedding model SpherE to address thi

Stats

• citations6
• S2 citations—
• github stars8
• HF likes0
• heat score8.25
• arxiv keyli2024sphere

Related papers

• 3D Shape Knowledge Graph For Cross-domain 3D Shape Retrieval (2022)5.24
• Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings (2022)11.85
• Answering Visual-relational Queries In Web-extracted Knowledge Graphs (2017)0.00
• Explore Entity Embedding Effectiveness In Entity Retrieval (2019)4.52
• SAGE: Structure Aware Graph Expansion For Retrieval Of Heterogeneous Data (2026)0.00
• Semantic Guided And Response Times Bounded Top-k Similarity Search Over Knowledge Graphs (2019)11.76
• Direct Fact Retrieval From Knowledge Graphs Without Entity Linking (2023)8.35
• Discrete Knowledge Graph Embedding Based On Discrete Optimization (2021)0.00