RLGNet:用于时序知识图谱推理的重复-局部-全局历史网络
RLGNet: Repeating-Local-Global History Network for Temporal Knowledge Graph Reasoning
AI总结:
本文提出基于集成学习的多尺度混合架构模型RLGNet,通过重复、局部和全局历史模块结合RNN与MLP,互补单步与多步推理能力并降低噪声影响,在六个基准数据集上优于现有TKG推理模型。
摘要:
时序知识图谱(TKG)推理涉及基于历史信息预测未来事件。然而,由于未来事件的不可预测性,该任务极具挑战性。为了解决这个问题,我们提出了一种基于集成学习的多尺度混合架构模型,称为 RLGNet(Repeating-Local-Global History Network,重复-局部-全局历史网络)。受多尺度信息在其他领域应用的启发,我们将多尺度信息的概念引入 TKG 推理。具体而言,RLGNet 通过结合处理各种尺度信息的模块,捕获并整合不同层次的历史信息。该模型包含三个模块:重复历史模块专注于识别历史数据中的重复模式和趋势,局部历史模块捕获短期变化和细节,全局历史模块提供对长期变化的宏观视角。此外,为了解决以往单架构模型在单步和多步推理任务泛化方面的局限性,我们分别为局部和全局历史模块采用了基于循环神经网络(RNN)和多层感知器(MLP)的架构。这种混合架构设计使模型能够互补多步和单步推理能力。最后,为了解决 TKG 中的噪声问题,我们采用集成学习策略,结合三个模块的预测结果,以降低噪声对最终预测结果的影响。在六个基准数据集上的评估中,我们的方法在多步和单步推理任务上总体优于现有的 TKG 推理模型。
英文摘要:
Temporal Knowledge Graph (TKG) reasoning involves predicting future events based on historical information. However, due to the unpredictability of future events, this task is highly challenging. To address this issue, we propose a multi-scale hybrid architecture model based on ensemble learning, called RLGNet (Repeating-Local-Global History Network). Inspired by the application of multi-scale information in other fields, we introduce the concept of multi-scale information into TKG reasoning. Specifically, RLGNet captures and integrates different levels of historical information by combining modules that process information at various scales. The model comprises three modules: the Repeating History Module focuses on identifying repetitive patterns and trends in historical data, the Local History Module captures short-term changes and details, and the Global History Module provides a macro perspective on long-term changes. Additionally, to address the limitations of previous single-architecture models in generalizing across single-step and multi-step reasoning tasks, we adopted architectures based on Recurrent Neural Networks (RNN) and Multi-Layer Perceptrons (MLP) for the Local and Global History Modules, respectively. This hybrid architecture design enables the model to complement both multi-step and single-step reasoning capabilities. Finally, to address the issue of noise in TKGs, we adopt an ensemble learning strategy, combining the predictions of the three modules to reduce the impact of noise on the final prediction results. In the evaluation on six benchmark datasets, our approach generally outperforms existing TKG reasoning models in multi-step and single-step reasoning 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。