Many knowledge graphs (KG) contain spatial and temporal information. Most KG embedding models follow triple-based representation and often neglect the simultaneous consideration of the spatial and temporal aspects. Encoding such higher dimensional knowledge necessitates the consideration of true algebraic and geometric aspects. Hypercomplex algebra provides the foundation of a well defined mathematical system among which the Dihedron algebra with its rich framework is suitable to handle multidimensional knowledge. In this paper, we propose an embedding model that uses Dihedron algebra for learning such spatial and temporal aspects. The evaluation results show that our model performs significantly better than other adapted models.
%0 Conference Paper
%1 nayyeri2022dihedron
%A Nayyeri, Mojtaba
%A Vahdati, Sahar
%A Khan, Md Tansen
%A Alam, Mirza Mohtashim
%A Wenige, Lisa
%A Behrend, Andreas
%A Lehmann, Jens
%B The Semantic Web
%C Cham
%D 2022
%E Groth, Paul
%E Vidal, Maria-Esther
%E Suchanek, Fabian
%E Szekley, Pedro
%E Kapanipathi, Pavan
%E Pesquita, Catia
%E Skaf-Molli, Hala
%E Tamper, Minna
%I Springer International Publishing
%K imported xack
%P 253--269
%T Dihedron Algebraic Embeddings for Spatio-Temporal Knowledge Graph Completion
%X Many knowledge graphs (KG) contain spatial and temporal information. Most KG embedding models follow triple-based representation and often neglect the simultaneous consideration of the spatial and temporal aspects. Encoding such higher dimensional knowledge necessitates the consideration of true algebraic and geometric aspects. Hypercomplex algebra provides the foundation of a well defined mathematical system among which the Dihedron algebra with its rich framework is suitable to handle multidimensional knowledge. In this paper, we propose an embedding model that uses Dihedron algebra for learning such spatial and temporal aspects. The evaluation results show that our model performs significantly better than other adapted models.
%@ 978-3-031-06981-9
@inproceedings{nayyeri2022dihedron,
abstract = {Many knowledge graphs (KG) contain spatial and temporal information. Most KG embedding models follow triple-based representation and often neglect the simultaneous consideration of the spatial and temporal aspects. Encoding such higher dimensional knowledge necessitates the consideration of true algebraic and geometric aspects. Hypercomplex algebra provides the foundation of a well defined mathematical system among which the Dihedron algebra with its rich framework is suitable to handle multidimensional knowledge. In this paper, we propose an embedding model that uses Dihedron algebra for learning such spatial and temporal aspects. The evaluation results show that our model performs significantly better than other adapted models.},
added-at = {2025-01-06T12:59:41.000+0100},
address = {Cham},
author = {Nayyeri, Mojtaba and Vahdati, Sahar and Khan, Md Tansen and Alam, Mirza Mohtashim and Wenige, Lisa and Behrend, Andreas and Lehmann, Jens},
biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/2ff739eddeb48f92ae96e32649ee0877c/scadsfct},
booktitle = {The Semantic Web},
editor = {Groth, Paul and Vidal, Maria-Esther and Suchanek, Fabian and Szekley, Pedro and Kapanipathi, Pavan and Pesquita, Catia and Skaf-Molli, Hala and Tamper, Minna},
interhash = {a5ba0c8ab3cc8686207d0ea7ca21e881},
intrahash = {ff739eddeb48f92ae96e32649ee0877c},
isbn = {978-3-031-06981-9},
keywords = {imported xack},
pages = {253--269},
publisher = {Springer International Publishing},
timestamp = {2025-08-21T11:39:34.000+0200},
title = {Dihedron Algebraic Embeddings for Spatio-Temporal Knowledge Graph Completion},
year = 2022
}