EMNLP Findings2025
Leveraging 3D Gaussian for Temporal Knowledge Graph Embedding
Jiang Li, Xiangdong Su, Guanglai Gao
Abstract
Representation learning in knowledge graphs (KGs) has predominantly focused on static data, yet many real-world knowledge graphs are inherently dynamic. For instance, the fact (The CEO of Apple, holds position, Steve Jobs) was valid until 2011, after which it changed, emphasizing the need to incorporate temporal information into knowledge representation. In this paper, we propose 3DG-TE, a novel temporal KG embedding method inspired by 3D Gaussian Splatting, where entities, relations, and timestamps are modeled as 3D Gaussian distributions with learnable structured covariance. This approach optimizes the Gaussian distributions of entities, relations, and timestamps to improve the overall KG representation. To effectively capture temporal-relational interactions, we design structured covariances that form composite transformation operators: relations induce rotational transformations, while timestamps regulate adaptive scaling. We also design a compound scoring function that integrates mean positions and structured covariance, preserving geometric interpretability. Experimental results on three benchmark TKG datasets demonstrate that 3DG-TE outperforms state-of-the-art baselines in temporal link prediction tasks. Theoretical analysis further confirms our model's ability to capture key relation patterns.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on13
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Diachronic Embedding for Temporal Knowledge Graph CompletionRishab Goel, Seyed Mehran Kazemi, Marcus A. Brubaker, Pascal PoupartAAAI 2020 · 423 citations
- Tensor Decompositions for Temporal Knowledge Base CompletionTimothée Lacroix, Guillaume Obozinski, Nicolas UsunierICLR 2020 · 341 citations
- Knowledge Graph Prompting for Multi-Document Question AnsweringYu Wang, Nedim Lipka, Ryan A. Rossi, Alexa F. Siu et al.AAAI 2024 · 290 citations
- Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge GraphJiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang et al.ICLR 2024 · 247 citations
Related papers
- HGE: Embedding Temporal Knowledge Graphs in a Product Space of Heterogeneous Geometric SubspacesJiaxin Pan, Mojtaba Nayyeri, Yinan Li, Steffen StaabAAAI 2024 · 22 citations
- Dual Quaternion Knowledge Graph EmbeddingsZongsheng Cao, Qianqian Xu, Zhiyong Yang, Xiaochun Cao et al.AAAI 2021 · 186 citations
- Hybrid Interaction Temporal Knowledge Graph Embedding Based on Householder TransformationsSensen Zhang, Xun Liang, Hui Tang, Zhenyu GuanACM MM 2023 · 6 citations
- Meta-Learning Based Knowledge Extrapolation for Temporal Knowledge GraphZhongwu Chen, Chengjin Xu, Fenglong Su, Zhen Huang et al.WWW 2023 · 18 citations
- RotateQVS: Representing Temporal Information as Rotations in Quaternion Vector Space for Temporal Knowledge Graph CompletionKai Chen, Ye Wang, Yitong Li, Aiping LiACL 2022
