计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (2): 331-341.doi: 10.11896/jsjkx.250100107

• 人工智能 • 上一篇    下一篇

基于背景结构感知的小样本知识图谱补全

张静, 潘景豪, 姜文超   

  1. 广东工业大学计算机学院 广州 510006
  • 收稿日期:2025-01-16 修回日期:2025-06-13 发布日期:2026-02-10
  • 通讯作者: 姜文超(jiangwenchao@gdut.edu.cn)
  • 作者简介:(844840296@qq.com)
  • 基金资助:
    国家自然科学基金重点项目(62237001);广东省自然科学基金(2024A1515011502);珠海市科技计划(2320004002758)

Background Structure-aware Few-shot Knowledge Graph Completion

ZHANG Jing, PAN Jinghao, JIANG Wenchao   

  1. School of Computer Science and Technology,Guangdong University of Technology,Guangzhou 510006,China
  • Received:2025-01-16 Revised:2025-06-13 Online:2026-02-10
  • About author:ZHANG Jing,born in 1972,postgra-duate,associate professor,master’s supervisor,is a member of CCF(No.K8905M).Her main research interests include big data,artificial intelligence,theories and applications of smart education,etc.JIANG Wenchao,born in 1977,Ph.D,associate professor,master’s supervisor,is a member of CCF(No.78409M).His main research interests include cloud computing and complex network.
  • Supported by:
    National Natural Science Foundation of China for Key Program (62237001),Natural Science Foundation of Guangdong Province,China(2024A1515011502) and Zhuhai Science and Technology Plan(2320004002758).

PDF (PC)

112

摘要： 小样本知识图谱补全旨在通过少量参考数据预测知识图谱中长尾关系的未知事实。如何在数据稀疏条件下高效编码实体和关系特征并构建有效的三元组评分函数对补全效果影响显著。现有的小样本知识图谱补全模型忽略了实体上下文背景结构信息对实体编码和评分函数的影响,导致关系表示学习能力不足。针对上述问题,提出了一种基于背景结构感知的小样本知识图谱补全模型(BSA)。首先,设计了一种实体对上下文背景结构信息交互指标,通过衡量邻居实体在结构上的影响,指导模型将注意力集中在与中心实体结构更相似的邻居节点,以减少噪声邻居的不良影响。其次,在关系表示学习阶段,引入背景知识图谱中语义和结构相似的关系信息进一步增强目标关系的嵌入表示。最后,在评分函数中引入头尾实体对的上下文信息交互指标,提升模型对复杂关系的推理能力。实验结果表明,与当前主流方法相比,BSA模型在NELL-One数据集测试中,MRR,Hit@5和Hit@1评价指标分别提高了0.4个百分点,0.8个百分点和0.5个百分点。在Wiki-One数据集测试中,MRR,Hit@10和Hit@5指标分别提高了1.9个百分点,2.2个百分点和2.2个百分点,充分证明了BSA模型的有效性。

关键词: 小样本知识图谱补全, 背景结构感知, 表示学习, 注意力机制

Abstract: Few-shot knowledge graph completion aims to predict unseen facts in long-tail relationships within knowledge graphs using only a small number of reference data.The key challenge of this task lies in how to efficiently encode entity and relation features under conditions of data scarcity,and to construct an effective triplet scoring function.Existing few-shot knowledge graph completion models generally overlook the impact of entity pair contextual information on both entity encoding and the scoring function,while also suffering from insufficient relation representation learning.To address these issues,this paper proposes a background-structure-aware few-shot knowledge graph completion model—BSA.Firstly,it designs a metric for entity pair contextual interaction,which guides the model to focus attention on neighbor nodes that are structurally similar to the central entity by measuring the structural influence of neighboring entities,thereby reducing the negative impact of noisy neighbors.Secondly,during the relation representation learning phase,it incorporates background relation information from the knowledge graph that is semantically and structurally similar to the target relation to enhance its embedding representation.Finally,it introduces a contextual interaction metric for the head-tail entity pair in the triplet scoring function to improve the model’s reasoning capability for complex relations.Experimental results show that,compared to the best results from baseline models,the BSA model improves MRR,Hit@5,and Hit@1 by 0.4 percentage points,0.8 percentage points,and 0.5 percentage points percentage points on the NELL-One dataset,respectively,and improves MRR,Hit@10,and Hit@5 by 1.9 percentage points,2.2 percentage points,and 2.2 percentage points on the Wiki-One dataset,respectively,demonstrating the effectiveness and feasibility of the proposed method.

Key words: Few-shot knowledge graph completion, Background structure-aware, Representation learning, Attention mechanism

中图分类号: 

  • TP391.1
[1]CHEN X,JIA S,XIANG Y.A review:Knowledge reasoningover knowledge graph[J].Expert Systems with Applications,2020,141(1):112948.
[2]FABIAN M S,GJERGJI K,GERHARD W.YAGO:a core ofsemantic knowledge[C]//Proceedings of the 16th international conference on World Wide Web.2007:697-706.
[3]TAN H,ZHAO H,LI R,et al.A Pipeline Approach to Free-Description Question Answering in Chinese Gaokao Reading Comprehension[J].Chinese Journal of Electronics,2019,28(1):113-119.
[4]LEHMANN J,ISELE R,JAKOB M,et al.DBpedia-A large-scale,multilingual knowledge base extracted from Wikipedia[J].Semantic Web,2015,6(2):167-195.
[5]SAXENA A,TRIPATHI A,TALUKDAR P.Improving Multi-hop Question Answering over Knowledge Graphs using Know-ledge Base Embeddings[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:4498-4507.
[6]WANG H,ZHANG F,ZHANG M,et al.KnowledgeawareGraph Neural Networks with Label Smoothness Regularization for Recommender Systems[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2019:968-977.
[7]NGUYEN D Q,VU T,NGUYEN T D,et al.Preparing Network Intrusion Detection Deep Learning Models with Minimal Data Using Adversarial Domain Adaptation[C]//Proceedings of the 15th ACM Asia Conference on Computer and Communications Security.2019:2180-2189.
[8]DONG X,GABRILOVICH E,HEITZ G,et al.Knowledgevault:a web-scale approach to probabilistic knowledge fusion[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2014:601-610.
[9]ZHANG N,DENG S,SUN Z,et al.Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational.2019:3016-3025.
[10]BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating Embeddings for Modeling Multi-relational Data[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems.2013:2787-2795.
[11]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.2014:1112-1119.
[12]YANG B,YIH W,HE X,et al.Embedding Entities and Relations for Learning and Inference in Knowledge Bases[J].arXiv:1412.6575,2014.
[13]TROUILLON T,WELBL J,RIEDEL S,et al.Complex Embeddings for Simple Link Prediction[C]//Proceedings of the 33rd International Conference on Machine Learning.2016:2071-2080.
[14]CHEN Z,WANG Y,ZHAO B,et al.Knowledge Graph Completion:A Review[J].IEEE Access,2020,8:192435-192456.
[15]CHICAIZA J,VALDIVIEZO-DIAZ P.A comprehensive survey of knowledge graph-based recommender systems:Technologies,development,and contributions[J].Information,2021,12(6):232.
[16]XIONG W,YU M,CHANG S,et al.One-Shot Relational Learning for Knowledge Graphs[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.ACL,2018:1980-1990.
[17]SHENG J,GUO S,CHEN Z,et al.Adaptive Attentional Network for Few-Shot Knowledge Graph Completion[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.ACL,2020:1681-1691.
[18]CHEN M,ZHANG W,ZHANG W,et al.Meta RelationalLearning for Few-Shot Link Prediction in Knowledge Graphs[C]//Proceedings of the 2019 Conference on Empirical Me-thods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.ACL,2019:4216-4225.
[19]HE T,ZHOU H,ONG Y,et al.Not All Neighbors Are Worth Attending to:Graph Selective Attention Networks for Semi-supervised Learning[J].arXiv:2210.07715,2022.
[20]ZHANG M,WANG X,ZHU M,et al.Robust HeterogeneousGraph Neural Networks against Adversarial Attacks[J].Proceedings of the AAAI Conference on Artificial Intelligence,2022,36(4):4363- 4370.
[21]ZHANG C,YAO H,HUANG C,et al.Few-Shot KnowledgeGraph Completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:3041-3048.
[22]LI Y,YU K,HUANG X,et al.Learning Inter-Entity-Interac-tion for Few-Shot Knowledge Graph Completion[C]//Procee-dings of the 2022 Conference on Empirical Methods in Natural Language Processing.2022:7691-7700.
[23]WANG J,WU T,ZHANG J.Incorporating Uncertainty of Entities and Relations into Few-Shot Uncertain Knowledge Graph Embedding[C]//China Conference on Knowledge Graph and Semantic Computing.Singapore:Springer,2022:16-28.
[24]LIU J,FAN C F,ZHOU F,et al.Complete feature learning and consistent relation modeling for few-shot knowledge graph completion[J].Expert Systems with Applications,2024,238:121725.
[25]NIU G,LI Y,TANG C,et al.Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval,ElectrNetwork.ACM,2021:213-222.
[26]XIE P,ZHOU G,LIU J,et al.Incorporating global-local neighbors with Gaussian mixture embedding for few-shot knowledge graph completion[J].Expert Systems with Applications,2023,234:121086.
[27]WU H,YIN J,RAJARATNAM B,et al.Hierarchical relational learning for few-shot knowledge graph completion[J].arXiv:2209.01205,2022.
[28]LUO L,LI Y F,HAFFARI G,et al.Normalizing flow-based neural process for few-shot knowledge graph completion[J].arXiv:2304.08183,2023.
[29]XU J,ZHANG J,KE X,et al.P-INT:A path-based interaction model for few-shot knowledge graph completion[C]//Findings of the Association for Computational Linguistics:EMNLP 2021.2021:385-394.
[30]MA R,WU H,WANG X,et al.Multi-view semantic enhancement model for few-shot knowledge graph completion[J].Expert Systems with Applications,2024,238:122086.
[31]LIANG Y,ZHAO S,CHENG B,et al.TransAM:Transformer appending matcher for few-shot knowledge graph completion[J].Neurocomputing,2023,537:61-72.
[32]LI Q,YAO J,TANG X,et al.Capsule neural tensor networks with multi-aspect information for Few-shot Knowledge Graph Completion[J].Neural Networks,2023,164:323-334.
[33]SCHLICHTKRULL M,KIPF T N,BLOEM P,et al.Modeling Relational Data with Graph Convolutional Networks[C]//5th Conference on Semantic Web Challenges(SemWebEval Challenge) at 15th Extended Semantic Web Conference(ESWC).Berlin:Springer,2018:593-607.
[34]NATHANI D,CHAUHAN J,SHARMA C,et al.Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics,Association for Computational Linguistics.2019:4710-4723.
[35]JAMBOR D,TERU K,PINEAU J,et al.Exploring the Limits of Few-Shot Link Prediction in Knowledge Graphs[J].arXiv:2102.03419,2021.
[36]LIN S,LU C H,JIANG W C,et al.Few-Shot Knowledge Graph Completion Based on Selective Attention[J].Journal of Frontiers of Computer Science & Technology,2024,18(3):646.
[37]LI M,SUN Z,ZHANG W.Slan:similarity-aware aggregation network for embedding out-of-knowledge-graph entities[J].Neurocomputing,2022,491:186-196.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发