HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations

by   Anson Bastos, et al.
Indian Institute of Technology Hyderabad
University of Dayton
RWTH Aachen University

Recently, several Knowledge Graph Embedding (KGE) approaches have been devised to represent entities and relations in dense vector space and employed in downstream tasks such as link prediction. A few KGE techniques address interpretability, i.e., mapping the connectivity patterns of the relations (i.e., symmetric/asymmetric, inverse, and composition) to a geometric interpretation such as rotations. Other approaches model the representations in higher dimensional space such as four-dimensional space (4D) to enhance the ability to infer the connectivity patterns (i.e., expressiveness). However, modeling relation and entity in a 4D space often comes at the cost of interpretability. This paper proposes HopfE, a novel KGE approach aiming to achieve the interpretability of inferred relations in the four-dimensional space. We first model the structural embeddings in 3D Euclidean space and view the relation operator as an SO(3) rotation. Next, we map the entity embedding vector from a 3D space to a 4D hypersphere using the inverse Hopf Fibration, in which we embed the semantic information from the KG ontology. Thus, HopfE considers the structural and semantic properties of the entities without losing expressivity and interpretability. Our empirical results on four well-known benchmarks achieve state-of-the-art performance for the KG completion task.


Knowledge Graph Embedding with Linear Representation for Link Prediction

Knowledge graph (KG) embedding aims to represent entities and relations ...

Inducing Interpretability in Knowledge Graph Embeddings

We study the problem of inducing interpretability in KG embeddings. Spec...

RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion

Many graph embedding approaches have been proposed for knowledge graph c...

AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding

Recent advances in Knowledge Graph Embed-ding (KGE) allow for representi...

DisenE: Disentangling Knowledge Graph Embeddings

Knowledge graph embedding (KGE), aiming to embed entities and relations ...

Knowledge Graph Embedding Bi-Vector Models for Symmetric Relation

Knowledge graph embedding (KGE) models have been proposed to improve the...

Please sign up or login with your details

Forgot password? Click here to reset