arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.07078cs.AIcs.DB
收藏

ADKGD:基于双通道训练的知识图谱异常检测

ADKGD: Anomaly Detection in Knowledge Graphs with Dual-Channel Training

Jinan University(暨南大学);South China Normal University(华南师范大学);University of Illinois Chicago(伊利诺伊大学芝加哥分校)

Jiayang Wu, Wensheng Gan, Jiahao Zhang, Philip S. Yu

AI总结:

针对知识图谱构建中易出现错误、影响下游任务及大语言模型可靠性的问题,本文提出双通道知识图谱异常检测算法ADKGD,通过双视角表示学习、跨层信息聚合及KL损失优化,在三个真实数据集上性能超越现有最优算法。

摘要:

在当前大语言模型(LLMs)的发展进程中,保障底层数据源的准确性与可靠性至关重要。大语言模型在各类应用中发挥着关键作用,但由于训练数据存在知识缺口,它们常出现幻觉与不准确的问题。知识图谱(KGs)作为一种强大的结构化工具,可作为重要的外部信息源来缓解上述问题。通过提供对真实世界数据的结构化、全面性理解,知识图谱能够提升大语言模型的性能与可靠性。然而,在从非结构化数据中提取三元组以构建知识图谱的过程中,知识图谱存在错误是常见现象。这可能导致问答、推荐系统等下游任务的性能下降。因此,知识图谱中的异常检测对于识别并纠正这些错误至关重要。本文提出了一种基于双通道学习的知识图谱异常检测算法ADKGD。ADKGD采用双通道学习方法,从实体视角和三元组视角两个维度增强表示学习。此外,本框架通过跨层方法,整合了内部信息聚合与上下文信息聚合。我们引入了库尔贝克-莱布勒(KL)损失组件,以提升双通道之间评分函数的准确性。为评估ADKGD的性能,我们在三个真实世界知识图谱上开展了实证研究:WN18RR、FB15K和NELL-995。实验结果表明,ADKGD的性能优于当前最先进的异常检测算法。源代码与数据集已公开于https://github.com/csjywu1/ADKGD。

英文摘要:

In the current development of large language models (LLMs), it is important to ensure the accuracy and reliability of the underlying data sources. LLMs are critical for various applications, but they often suffer from hallucinations and inaccuracies due to knowledge gaps in the training data. Knowledge graphs (KGs), as a powerful structural tool, could serve as a vital external information source to mitigate the aforementioned issues. By providing a structured and comprehensive understanding of real-world data, KGs enhance the performance and reliability of LLMs. However, it is common that errors exist in KGs while extracting triplets from unstructured data to construct KGs. This could lead to degraded performance in downstream tasks such as question-answering and recommender systems. Therefore, anomaly detection in KGs is essential to identify and correct these errors. This paper presents an anomaly detection algorithm in knowledge graphs with dual-channel learning (ADKGD). ADKGD leverages a dual-channel learning approach to enhance representation learning from both the entity-view and triplet-view perspectives. Furthermore, using a cross-layer approach, our framework integrates internal information aggregation and context information aggregation. We introduce a kullback-leibler (KL)-loss component to improve the accuracy of the scoring function between the dual channels. To evaluate ADKGD's performance, we conduct empirical studies on three real-world KGs: WN18RR, FB15K, and NELL-995. Experimental results demonstrate that ADKGD outperforms the state-of-the-art anomaly detection algorithms. The source code and datasets are publicly available at https://github.com/csjywu1/ADKGD.

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。

↑