TeDS: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph Completion

Jiujiang Guo, Mankun Zhao, Wenbin Zhang, Tianyi Xu, Linying Xu, Yu Jian, Yu Mei, Yu Ruiguo
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:21232-21251, 2025.

Abstract

Existing research on temporal knowledge graph completion treats temporal information as supplementary, without simulating various features of facts from a temporal perspective. This work summarizes features of temporalized facts from both diachronic and synchronic perspectives: (1) Diachronicity. Facts often exhibit varying characteristics and trends across different temporal domains; (2) Synchronicity. In specific temporal contexts, various relations between entities influence each other, generating latent semantics. To track above issues, we design a quaternion-based model, TeDS, which divides timestamps into diachronic and synchronic timestamps to support dual temporal perception: (a) Two composite quaternions fusing time and relation information are generated by reorganizing synchronic timestamp and relation quaternions, and Hamilton operator achieves their interaction. (b) Each time point is sequentially mapped to an angle and converted to scalar component of a quaternion using trigonometric functions to build diachronic timestamps. We then rotate relation by using Hamilton operator between it and diachronic timestamp. In this way, TeDS achieves deep integration of relations and time while accommodating different perspectives. Empirically, TeDS significantly outperforms SOTA models on six benchmarks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-guo25u, title = {{T}e{DS}: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph Completion}, author = {Guo, Jiujiang and Zhao, Mankun and Zhang, Wenbin and Xu, Tianyi and Xu, Linying and Jian, Yu and Mei, Yu and Ruiguo, Yu}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {21232--21251}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/guo25u/guo25u.pdf}, url = {https://proceedings.mlr.press/v267/guo25u.html}, abstract = {Existing research on temporal knowledge graph completion treats temporal information as supplementary, without simulating various features of facts from a temporal perspective. This work summarizes features of temporalized facts from both diachronic and synchronic perspectives: (1) Diachronicity. Facts often exhibit varying characteristics and trends across different temporal domains; (2) Synchronicity. In specific temporal contexts, various relations between entities influence each other, generating latent semantics. To track above issues, we design a quaternion-based model, TeDS, which divides timestamps into diachronic and synchronic timestamps to support dual temporal perception: (a) Two composite quaternions fusing time and relation information are generated by reorganizing synchronic timestamp and relation quaternions, and Hamilton operator achieves their interaction. (b) Each time point is sequentially mapped to an angle and converted to scalar component of a quaternion using trigonometric functions to build diachronic timestamps. We then rotate relation by using Hamilton operator between it and diachronic timestamp. In this way, TeDS achieves deep integration of relations and time while accommodating different perspectives. Empirically, TeDS significantly outperforms SOTA models on six benchmarks.} }
Endnote
%0 Conference Paper %T TeDS: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph Completion %A Jiujiang Guo %A Mankun Zhao %A Wenbin Zhang %A Tianyi Xu %A Linying Xu %A Yu Jian %A Yu Mei %A Yu Ruiguo %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-guo25u %I PMLR %P 21232--21251 %U https://proceedings.mlr.press/v267/guo25u.html %V 267 %X Existing research on temporal knowledge graph completion treats temporal information as supplementary, without simulating various features of facts from a temporal perspective. This work summarizes features of temporalized facts from both diachronic and synchronic perspectives: (1) Diachronicity. Facts often exhibit varying characteristics and trends across different temporal domains; (2) Synchronicity. In specific temporal contexts, various relations between entities influence each other, generating latent semantics. To track above issues, we design a quaternion-based model, TeDS, which divides timestamps into diachronic and synchronic timestamps to support dual temporal perception: (a) Two composite quaternions fusing time and relation information are generated by reorganizing synchronic timestamp and relation quaternions, and Hamilton operator achieves their interaction. (b) Each time point is sequentially mapped to an angle and converted to scalar component of a quaternion using trigonometric functions to build diachronic timestamps. We then rotate relation by using Hamilton operator between it and diachronic timestamp. In this way, TeDS achieves deep integration of relations and time while accommodating different perspectives. Empirically, TeDS significantly outperforms SOTA models on six benchmarks.
APA
Guo, J., Zhao, M., Zhang, W., Xu, T., Xu, L., Jian, Y., Mei, Y. & Ruiguo, Y.. (2025). TeDS: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph Completion. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:21232-21251 Available from https://proceedings.mlr.press/v267/guo25u.html.

Related Material