Saved in:
Bibliographic Details
Main Authors: Shen, Jiawei, Zhu, Jia, Guo, Hanghui, Shi, Weijie, Ma, Guoqing, Liang, Yidan, Liu, Jingjiang, Chen, Hao, Di, Shimin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.12669
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915717774835712
author Shen, Jiawei
Zhu, Jia
Guo, Hanghui
Shi, Weijie
Ma, Guoqing
Liang, Yidan
Liu, Jingjiang
Chen, Hao
Di, Shimin
author_facet Shen, Jiawei
Zhu, Jia
Guo, Hanghui
Shi, Weijie
Ma, Guoqing
Liang, Yidan
Liu, Jingjiang
Chen, Hao
Di, Shimin
contents Temporal Knowledge Graph Reasoning (TKGR) aims to complete missing factual elements along the timeline. Depending on the temporal position of the query, the task is categorized into interpolation and extrapolation. Existing interpolation methods typically embed temporal information into individual facts to complete missing historical knowledge, while extrapolation techniques often leverage sequence models over graph snapshots to identify recurring patterns for future event prediction. These methods face two critical challenges: limited contextual modeling in interpolation and cognitive generalization bias in extrapolation. To address these, we propose a unified method for TKGR, dubbed DynaGen. For interpolation, DynaGen dynamically constructs entity-centric subgraphs and processes them with a synergistic dual-branch GNN encoder to capture evolving structural context. For extrapolation, it applies a conditional diffusion process, which forces the model to learn underlying evolutionary principles rather than just superficial patterns, enhancing its ability to predict unseen future events. Extensive experiments on six benchmark datasets show DynaGen achieves state-of-the-art performance. On average, compared to the second-best models, DynaGen improves the Mean Reciprocal Rank (MRR) score by 2.61 points for interpolation and 1.45 points for extrapolation.
format Preprint
id arxiv_https___arxiv_org_abs_2512_12669
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DynaGen: Unifying Temporal Knowledge Graph Reasoning with Dynamic Subgraphs and Generative Regularization
Shen, Jiawei
Zhu, Jia
Guo, Hanghui
Shi, Weijie
Ma, Guoqing
Liang, Yidan
Liu, Jingjiang
Chen, Hao
Di, Shimin
Machine Learning
Artificial Intelligence
Temporal Knowledge Graph Reasoning (TKGR) aims to complete missing factual elements along the timeline. Depending on the temporal position of the query, the task is categorized into interpolation and extrapolation. Existing interpolation methods typically embed temporal information into individual facts to complete missing historical knowledge, while extrapolation techniques often leverage sequence models over graph snapshots to identify recurring patterns for future event prediction. These methods face two critical challenges: limited contextual modeling in interpolation and cognitive generalization bias in extrapolation. To address these, we propose a unified method for TKGR, dubbed DynaGen. For interpolation, DynaGen dynamically constructs entity-centric subgraphs and processes them with a synergistic dual-branch GNN encoder to capture evolving structural context. For extrapolation, it applies a conditional diffusion process, which forces the model to learn underlying evolutionary principles rather than just superficial patterns, enhancing its ability to predict unseen future events. Extensive experiments on six benchmark datasets show DynaGen achieves state-of-the-art performance. On average, compared to the second-best models, DynaGen improves the Mean Reciprocal Rank (MRR) score by 2.61 points for interpolation and 1.45 points for extrapolation.
title DynaGen: Unifying Temporal Knowledge Graph Reasoning with Dynamic Subgraphs and Generative Regularization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.12669