arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.01477cs.LGcs.CL
收藏

DPCL-Diff:基于双域周期对比学习的图节点扩散模型的时序知识图谱推理

DPCL-Diff: The Temporal Knowledge Graph Reasoning Based on Graph Node Diffusion Model with Dual-Domain Periodic Contrastive Learning

Shanghai University of Electric Power(上海电力大学)

Yukun Cao, Lisheng Wang, Luobin Huang

AI总结:

针对历史交互稀疏的未来时序知识图谱推理效果不佳的问题,提出结合双域周期对比学习的图节点扩散模型DPCL-Diff,通过生成高质量数据和双空间映射提升推理性能,在四个公开数据集上优于现有最优模型。

摘要:

时序知识图谱(TKG)推理旨在推断未来缺失的事实,是一项重要且具有挑战性的任务。预测未来事件通常依赖于密切相关的历史事实,对于重复性或周期性事件能产生更准确的结果。然而,对于历史交互稀疏的未来事件,这种侧重于利用高频历史信息的方法的有效性会下降。近年来,扩散模型在图像生成中的能力为TKG推理开辟了新的机遇。因此,我们提出了一种带有双域周期对比学习的图节点扩散模型(DPCL-Diff)。图节点扩散模型(GNDiff)向稀疏相关事件中引入噪声以模拟新事件,生成更符合实际分布的高质量数据。这种生成机制显著增强了模型对新事件的推理能力。此外,双域周期对比学习(DPCL)将周期性和非周期性事件实体映射到庞加莱空间和欧几里得空间,利用它们的特性有效区分相似的周期性事件。在四个公开数据集上的实验结果表明,DPCL-Diff在事件预测方面显著优于最先进的TKG模型,证明了我们方法的有效性。本研究还探究了GNDiff和DPCL在TKG任务中的联合效能。

英文摘要:

Temporal knowledge graph (TKG) reasoning that infers future missing facts is an essential and challenging task. Predicting future events typically relies on closely related historical facts, yielding more accurate results for repetitive or periodic events. However, for future events with sparse historical interactions, the effectiveness of this method, which focuses on leveraging high-frequency historical information, diminishes. Recently, the capabilities of diffusion models in image generation have opened new opportunities for TKG reasoning. Therefore, we propose a graph node diffusion model with dual-domain periodic contrastive learning (DPCL-Diff). Graph node diffusion model (GNDiff) introduces noise into sparsely related events to simulate new events, generating high-quality data that better conforms to the actual distribution. This generative mechanism significantly enhances the model's ability to reason about new events. Additionally, the dual-domain periodic contrastive learning (DPCL) maps periodic and non-periodic event entities to Poincaré and Euclidean spaces, leveraging their characteristics to distinguish similar periodic events effectively. Experimental results on four public datasets demonstrate that DPCL-Diff significantly outperforms state-of-the-art TKG models in event prediction, demonstrating our approach's effectiveness. This study also investigates the combined effectiveness of GNDiff and DPCL in TKG tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑