具有可解释性的时态知识图谱异常在线检测

Jiasheng Zhang, Jie Shao, Rex Ying
{"title":"具有可解释性的时态知识图谱异常在线检测","authors":"Jiasheng Zhang, Jie Shao, Rex Ying","doi":"arxiv-2408.00872","DOIUrl":null,"url":null,"abstract":"Temporal knowledge graphs (TKGs) are valuable resources for capturing\nevolving relationships among entities, yet they are often plagued by noise,\nnecessitating robust anomaly detection mechanisms. Existing dynamic graph\nanomaly detection approaches struggle to capture the rich semantics introduced\nby node and edge categories within TKGs, while TKG embedding methods lack\ninterpretability, undermining the credibility of anomaly detection. Moreover,\nthese methods falter in adapting to pattern changes and semantic drifts\nresulting from knowledge updates. To tackle these challenges, we introduce\nAnoT, an efficient TKG summarization method tailored for interpretable online\nanomaly detection in TKGs. AnoT begins by summarizing a TKG into a novel rule\ngraph, enabling flexible inference of complex patterns in TKGs. When new\nknowledge emerges, AnoT maps it onto a node in the rule graph and traverses the\nrule graph recursively to derive the anomaly score of the knowledge. The\ntraversal yields reachable nodes that furnish interpretable evidence for the\nvalidity or the anomalous of the new knowledge. Overall, AnoT embodies a\ndetector-updater-monitor architecture, encompassing a detector for offline TKG\nsummarization and online scoring, an updater for real-time rule graph updates\nbased on emerging knowledge, and a monitor for estimating the approximation\nerror of the rule graph. Experimental results on four real-world datasets\ndemonstrate that AnoT surpasses existing methods significantly in terms of\naccuracy and interoperability. All of the raw datasets and the implementation\nof AnoT are provided in https://github.com/zjs123/ANoT.","PeriodicalId":501123,"journal":{"name":"arXiv - CS - Databases","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Online Detection of Anomalies in Temporal Knowledge Graphs with Interpretability\",\"authors\":\"Jiasheng Zhang, Jie Shao, Rex Ying\",\"doi\":\"arxiv-2408.00872\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Temporal knowledge graphs (TKGs) are valuable resources for capturing\\nevolving relationships among entities, yet they are often plagued by noise,\\nnecessitating robust anomaly detection mechanisms. Existing dynamic graph\\nanomaly detection approaches struggle to capture the rich semantics introduced\\nby node and edge categories within TKGs, while TKG embedding methods lack\\ninterpretability, undermining the credibility of anomaly detection. Moreover,\\nthese methods falter in adapting to pattern changes and semantic drifts\\nresulting from knowledge updates. To tackle these challenges, we introduce\\nAnoT, an efficient TKG summarization method tailored for interpretable online\\nanomaly detection in TKGs. AnoT begins by summarizing a TKG into a novel rule\\ngraph, enabling flexible inference of complex patterns in TKGs. When new\\nknowledge emerges, AnoT maps it onto a node in the rule graph and traverses the\\nrule graph recursively to derive the anomaly score of the knowledge. The\\ntraversal yields reachable nodes that furnish interpretable evidence for the\\nvalidity or the anomalous of the new knowledge. Overall, AnoT embodies a\\ndetector-updater-monitor architecture, encompassing a detector for offline TKG\\nsummarization and online scoring, an updater for real-time rule graph updates\\nbased on emerging knowledge, and a monitor for estimating the approximation\\nerror of the rule graph. Experimental results on four real-world datasets\\ndemonstrate that AnoT surpasses existing methods significantly in terms of\\naccuracy and interoperability. All of the raw datasets and the implementation\\nof AnoT are provided in https://github.com/zjs123/ANoT.\",\"PeriodicalId\":501123,\"journal\":{\"name\":\"arXiv - CS - Databases\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Databases\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.00872\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Databases","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.00872","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

时态知识图谱(TKG)是捕捉实体间不断变化的关系的宝贵资源,但它们经常受到噪声的困扰,因此需要强大的异常检测机制。现有的动态图异常检测方法难以捕捉 TKG 中节点和边的类别所引入的丰富语义,而 TKG 嵌入方法缺乏可解释性,从而削弱了异常检测的可信度。此外,这些方法在适应知识更新导致的模式变化和语义漂移方面也存在缺陷。为了应对这些挑战,我们引入了一种高效的 TKG 总结方法 AnoT,它是为 TKG 中可解释的在线异常检测而量身定制的。AnoT 首先将 TKG 总结为一个新颖的规则图,从而能够灵活推断 TKG 中的复杂模式。当出现新知识时,AnoT 会将其映射到规则图中的节点上,并递归遍历规则图,从而得出该知识的异常得分。遍历产生的可到达节点为新知识的有效性或异常性提供了可解释的证据。总的来说,AnoT 包含一个检测器-更新器-监控器架构,其中包括一个用于离线 TKGs 总结和在线评分的检测器、一个用于根据新知识实时更新规则图的更新器和一个用于估计规则图近似误差的监控器。在四个真实数据集上的实验结果表明,AnoT 在准确性和互操作性方面大大超过了现有方法。所有原始数据集和 AnoT 的实现都在 https://github.com/zjs123/ANoT 中提供。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Online Detection of Anomalies in Temporal Knowledge Graphs with Interpretability
Temporal knowledge graphs (TKGs) are valuable resources for capturing evolving relationships among entities, yet they are often plagued by noise, necessitating robust anomaly detection mechanisms. Existing dynamic graph anomaly detection approaches struggle to capture the rich semantics introduced by node and edge categories within TKGs, while TKG embedding methods lack interpretability, undermining the credibility of anomaly detection. Moreover, these methods falter in adapting to pattern changes and semantic drifts resulting from knowledge updates. To tackle these challenges, we introduce AnoT, an efficient TKG summarization method tailored for interpretable online anomaly detection in TKGs. AnoT begins by summarizing a TKG into a novel rule graph, enabling flexible inference of complex patterns in TKGs. When new knowledge emerges, AnoT maps it onto a node in the rule graph and traverses the rule graph recursively to derive the anomaly score of the knowledge. The traversal yields reachable nodes that furnish interpretable evidence for the validity or the anomalous of the new knowledge. Overall, AnoT embodies a detector-updater-monitor architecture, encompassing a detector for offline TKG summarization and online scoring, an updater for real-time rule graph updates based on emerging knowledge, and a monitor for estimating the approximation error of the rule graph. Experimental results on four real-world datasets demonstrate that AnoT surpasses existing methods significantly in terms of accuracy and interoperability. All of the raw datasets and the implementation of AnoT are provided in https://github.com/zjs123/ANoT.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信