Aug 12, 2021 · This paper proposes HopfE, a novel KGE approach aiming to achieve the interpretability of inferred relations in the four-dimensional space.

We propose HopfE, a novel KGE approach aiming to achieve the interpretability of inferred relations in the four-dimensional space. HopfE models the structural ...

HopfE considers the structural and semantic properties of the entities without losing expressivity and interpretability in the four-dimensional space, ...

Aug 12, 2021 · 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 ...

HopfE (Bastos et al., 2021) views relations as SO(3) rotations and uses the inverse Hopf fibration to map entities from 3D Euclidean space to 4D hypersphere.

HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations ; CIKM '21: The 30th ACM International Conference on Information and Knowledge ...

HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations. HopfE considers the structural and semantic properties of the entities without ...

HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations. A Bastos, K Singh, A Nadgeri, S Shekarpour, IO Mulang, J Hoffart. CIKM 2021: 30th ...

The goal of Graph Representation Learning is to construct a set of features ('embeddings') representing the structure of the graph and the data thereon.

Hopfe: Knowledge graph representation learning using inverse hopf fibrations. A Bastos, K Singh, A Nadgeri, S Shekarpour, IO Mulang, J Hoffart. Proceedings of ...