Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction

Yadong Sun, Xiaofeng Cao, Ivor Tsang, Heng Tao Shen
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57336-57354, 2025.

Abstract

Static systems exhibit diverse structural properties, such as hierarchical, scale-free, and isotropic patterns, where different geometric spaces offer unique advantages. Methods combining multiple geometries have proven effective in capturing these characteristics. However, real-world systems often evolve dynamically, introducing significant challenges in modeling their temporal changes. To overcome this limitation, we propose a unified cross-geometric learning framework for dynamic systems, which synergistically integrates Euclidean and hyperbolic spaces, aligning embedding spaces with structural properties through fine-grained substructure modeling. Our framework further incorporates a temporal state aggregation mechanism and an evolution-driven optimization objective, enabling comprehensive and adaptive modeling of both nodal and relational dynamics over time. Extensive experiments on diverse real-world dynamic graph datasets highlight the superiority of our approach in capturing complex structural evolution, surpassing existing methods across multiple metrics.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-sun25a, title = {Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction}, author = {Sun, Yadong and Cao, Xiaofeng and Tsang, Ivor and Shen, Heng Tao}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {57336--57354}, 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/sun25a/sun25a.pdf}, url = {https://proceedings.mlr.press/v267/sun25a.html}, abstract = {Static systems exhibit diverse structural properties, such as hierarchical, scale-free, and isotropic patterns, where different geometric spaces offer unique advantages. Methods combining multiple geometries have proven effective in capturing these characteristics. However, real-world systems often evolve dynamically, introducing significant challenges in modeling their temporal changes. To overcome this limitation, we propose a unified cross-geometric learning framework for dynamic systems, which synergistically integrates Euclidean and hyperbolic spaces, aligning embedding spaces with structural properties through fine-grained substructure modeling. Our framework further incorporates a temporal state aggregation mechanism and an evolution-driven optimization objective, enabling comprehensive and adaptive modeling of both nodal and relational dynamics over time. Extensive experiments on diverse real-world dynamic graph datasets highlight the superiority of our approach in capturing complex structural evolution, surpassing existing methods across multiple metrics.} }
Endnote
%0 Conference Paper %T Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction %A Yadong Sun %A Xiaofeng Cao %A Ivor Tsang %A Heng Tao Shen %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-sun25a %I PMLR %P 57336--57354 %U https://proceedings.mlr.press/v267/sun25a.html %V 267 %X Static systems exhibit diverse structural properties, such as hierarchical, scale-free, and isotropic patterns, where different geometric spaces offer unique advantages. Methods combining multiple geometries have proven effective in capturing these characteristics. However, real-world systems often evolve dynamically, introducing significant challenges in modeling their temporal changes. To overcome this limitation, we propose a unified cross-geometric learning framework for dynamic systems, which synergistically integrates Euclidean and hyperbolic spaces, aligning embedding spaces with structural properties through fine-grained substructure modeling. Our framework further incorporates a temporal state aggregation mechanism and an evolution-driven optimization objective, enabling comprehensive and adaptive modeling of both nodal and relational dynamics over time. Extensive experiments on diverse real-world dynamic graph datasets highlight the superiority of our approach in capturing complex structural evolution, surpassing existing methods across multiple metrics.
APA
Sun, Y., Cao, X., Tsang, I. & Shen, H.T.. (2025). Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:57336-57354 Available from https://proceedings.mlr.press/v267/sun25a.html.

Related Material