3. B. Xiong
et al., “Ultrahyperbolic Knowledge Graph Embeddings,” in
28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD-22, in 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD-22. Aug. 2022. doi:
https://doi.org/10.1145/3534678.3539333.
Abstract
Recent knowledge graph (KG) embeddings have been advanced by hyperbolic geometry due to its superior capability for representing hierarchies. The topological structures of real-world KGs, however, are rather heterogeneous, i.e., a KG is composed of multiple distinct hierarchies and non-hierarchical graph structures. Therefore, a homogeneous (either Euclidean or hyperbolic) geometry is not sufficient for fairly representing such heterogeneous structures. To capture the topological heterogeneity of KGs, we present an ultrahyperbolic KG embedding (UltraE) in an ultrahyperbolic (or pseudo-Riemannian) manifold that seamlessly interleaves hyperbolic and spherical manifolds. In particular, we model each relation as a pseudo-orthogonal transformation that preserves the pseudo-Riemannian bilinear form. The pseudo-orthogonal transformation is decomposed into various operators (i.e., circular rotations, reflections and hyperbolic rotations), allowing for simultaneously modeling heterogeneous structures as well as complex relational patterns. Experimental results on three standard KGs show that UltraE outperforms previous Euclidean, hyperbolic, and mixed-curvature KG embedding approaches.BibTeX
2. C. Xu, M. Nayyeri, F. Alkhoury, H. Yazdi, and J. Lehmann, “Temporal Knowledge Graph Completion Based on Time Series Gaussian Embedding,” in
Lecture Notes in Computer Science, in Lecture Notes in Computer Science. Springer International Publishing, 2020, pp. 654--671. doi:
10.1007/978-3-030-62419-4_37.
BibTeX
1. M. Nayyeri, M. M. Alam, J. Lehmann, and S. Vahdati, “3D Learning and Reasoning in Link Prediction Over Knowledge Graphs,”
IEEE Access, vol. 8, pp. 196459--196471, 2020, doi:
10.1109/access.2020.3034183.
BibTeX
