国网南京供电公司;国网南通供电公司;国网智能电网研究院有限公司;苏州华天国科电力科技有限公司;
知识图谱嵌入(Knowledge Graph Embedding, KGE)将实体和关系表示为低维、连续的向量，使机器学习模型能够轻松适应知识图谱(Knowledge Graph, KG)的搜索任务。然而，在大规模知识库(Knowledge Base, KB)的搜索密集型应用中，现有的模型大多侧重于提高在静态KG上搜索的准确性，忽略了在动态时态知识图谱(Temporal Knowledge Graph, TKG)上搜索的时间效率。为此，提出了一种向量索引支持的TKG高效搜索方法，以提高在TKG上的搜索效率。具体来说，首先，将实体，关系和时间信息映射到向量空间，并利用长短期记忆神经网络(Long Short-Term Memory, LSTM)学习关系类型的时间感知，从而建立了具有时间信息感知与关系联合编码的TKG向量库。然后，利用向量数据库建立大规模TKG的向量索引库(IndexIVFFlat)。注意，该索引通过聚类操作来划分搜索空间，以提高知识的搜索效率。最后，在拥有高效索引的TKG上通过相似度计算执行近似性搜索与实验评估。结果显示，该方法在时间效率上优于未建立索引的方法，且在搜索准确度上优于一些强相关的方法。表明，该向量索引库的建立在保证了搜索准确性的前提下提高了在TKG上的搜索效率。
| 196 | 0 | 6 |
| 下载次数 | 被引频次 | 阅读次数 |
[1] SUN J,CHEN J,DING G,et al.Spectrum recommendation in cognitive internet of things:a knowledge-graph-based framework[J].IEEE Transactions on Cognitive Communications and Networking,2024,10(1):21-34.
[2] TAN S,GE M,GUO D,et al.Knowledge-based embodied question answering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2023,45(10):11948-11960.
[3] SUN Y,WANG J,LIN H,et al.Knowledge guided attention and graph convolutional networks for chemical-disease relation extraction[J].IEEE/ACM Transactions on Computational Biology and Bioinformatics,2021,20(1):489-499.
[4] 毛慧慧，赵小乐，杜圣东，等.基于时序知识图谱嵌入的短期地铁客流量预测[J].计算机科学，2023,50(7):213-220.
[5] WANG Q,MAO Z,WANG B,et al.Knowledge graph embedding:a survey of approaches and applications[J].IEEE Transactions on Knowledge and Data Engineering,2017,29(12):2724-2743.
[6] JI S,PAN S,CAMBRIA E,et al.A survey on knowledge graphs:representation,acquisition,and applications[J].IEEE Transactions on Neural Networks and Learning Systems,2021,33(2):494-514.
[7] BORDES A,USUNIER N,GARCIA-DURáN A,et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of the 26th international conference on neural information processing systems.Lake Tahoe:Curran Associates Inc,2013:2787-2795.
[8] WANG Z,ZHANG J,FENG J,et al.Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the twenty-eighth AAAI conference on artificial intelligence.Québec City:AAAI,2014:1112-1119.
[9] LIN Y,LIU Z,SUN M,et al.Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of the twenty-ninth AAAI conference on artificial intelligence.Austin:AAAI,2015:2181-2187.
[10] SUN Z,DENG Z H,NIE J Y,et al.RotatE:knowledge graph embedding by relational rotation in complex space[C]//International conference on learning representations.New Orleans:OpenReview,2018:1-18.
[11] 熊伟，陈浩，苏鸿宇.QuatCNNEx:一种面向多关系模式的知识图谱嵌入模型[J/OL].计算机学报：1-11[2024-08-17].http://kns.cnki.net/kcms/detail/11.1826.tp.20240701.1016.002.html.
[12] DASGUPTA S S,RAY S N,TALUKDAR P.Hyte:hyperplane-based temporally aware knowledge graph embedding[C]//Proceedings of the 2018 conference on empirical methods in natural language processing.Brussels:Association for Computational Linguistics,2018:2001-2011.
[13] XU C,NAYYERI M,ALKHOURY F,et al.TeRo:a time-aware knowledge graph embedding via temporal rotation[C]//Proceedings of the 28th international conference on computational linguistics.Barcelona:International Committee on Computational Linguistics,2020:1583-1593.
[14] XU C,NAYYERI M,CHEN Y Y,et al.Geometric algebra based embeddings for static and temporal knowledge graph completion[J].IEEE Transactions on Knowledge and Data Engineering,2022,35(5):4838-4851.
[15] GARCIA-DURAN A,DUMAN■.Learning sequence encoders for temporal knowledge graph completion[C]//Proceedings of the 2018 conference on empirical methods in natural language processing.Brussels:Association for Computational Linguistics,2018:4816-4821.
[16] HOU X,MA R,YAN L,et al.T-gae:a timespan-aware graph attention-based embedding model for temporal knowledge graph completion[J].Information Sciences,2023,642:119225.
[17] WANG M,CHEN W,WANG S,et al.Efficient search over incomplete knowledge graphs in binarized embedding space[J].Future Generation Computer Systems,2021,123:24-34.
[18] BAI Y,LV X,LI J,et al.Answering complex logical queries on knowledge graphs via query computation tree optimization[C]//International conference on machine learning.Honolulu:PMLR,2023:1472-1491.
[19] 陈小英，熊盛武，王盛，等.基于上下文时序关联的时序知识图谱嵌入方法[J].武汉大学学报：理学版，2023,69(2):249-257.
[20] WANG M,SHEN H,WANG S,et al.Learning to hash for efficient search over incomplete knowledge graphs[C]//2019 IEEE international conference on data mining (ICDM).Beijing:IEEE,2019:1360-1365.
[21] WANG M,WU T,QI G.A hash learning framework for search-oriented knowledge graph embedding[C]//European conference on artificial intelligence.Santiago de Compostela:IOS Press,2020:921-928.
[22] ABUODA G,THIRUMURUGANATHAN S,ABOULNAGA A.Accelerating entity lookups in knowledge graphs through embeddings[C]//2022 IEEE 38th international conference on data engineering (ICDE).Kuala Lumpur:IEEE,2022:1111-1123.
[23] OBRACZKA D,RAHM E.Fast hubness-reduced nearest neighbor search for entity alignment in knowledge graphs[J].SN Computer Science,2022,3(6):501.
[24] LEBLAY J,CHEKOL M W.Deriving validity time in knowledge graph[C]//Companion proceedings of the web conference.Lyon:ACM,2018:1771-1776.
基本信息:
DOI：10.20165/j.cnki.ISSN1673-629X.2024.0305
中图分类号:TP181;TP391.1
引用信息:
[1]朱红,胡新雨,高莉莎等.一种向量索引支持的时态知识图谱高效搜索方法[J].计算机技术与发展,2025,35(02):138-145.DOI:10.20165/j.cnki.ISSN1673-629X.2024.0305.
基金信息:
国家电网公司总部科技项目(5700-202318598A-3-2-ZN)