计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (5): 223-231.doi: 10.11896/jsjkx.230200012

• 人工智能 • 上一篇    下一篇

基于自适应上下文匹配网络的小样本知识图谱补全

杨旭华, 张炼, 叶蕾   

  1. 浙江工业大学计算机科学与技术学院 杭州 310023
  • 收稿日期:2023-02-02 修回日期:2023-05-18 出版日期:2024-05-15 发布日期:2024-05-08
  • 通讯作者: 叶蕾(yelei@zjut.edu.cn)
  • 作者简介:(xhyang@zjut.edu.cn)
  • 基金资助:
    国家自然科学基金(62176236)

Adaptive Context Matching Network for Few-shot Knowledge Graph Completion

YANG Xuhua, ZHANG Lian, YE Lei   

  1. College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China
  • Received:2023-02-02 Revised:2023-05-18 Online:2024-05-15 Published:2024-05-08
  • About author:YANG Xuhua,born in 1971,Ph.D,professor,is a senior member of CCF(No.17093S).His main research interests include machine learning,network science and natural language processing.
    YE Lei,born in 1979,Ph.D,associate professor,is a member of CCF(No.80067M).Her main research interests include data mining and knowledge reasoning.
  • Supported by:
    National Natural Science Foundation of China(62176236).

PDF (PC)

374

摘要： 知识图谱在构建过程中需要面对繁杂的现实世界信息,无法建模所有知识,因此需要补全。真实的知识图谱中很多类型的关系通常只有少量的训练实体样本对。因此,如何进行小样本知识图谱补全是一个十分有价值的问题。目前基于嵌入的方法一般通过注意力机制等方法聚合实体上下文信息,通过学习关系嵌入的方式来补全知识图谱,仅考虑关系层面的匹配程度,虽然能够预测未知关系,但往往准确度不高。针对小样本知识图谱补全问题,提出了一个自适应上下文匹配网络(Adaptive Context Matching Network,ACMN)。首先提出一个共性邻居感知编码器,聚合参考集实体上下文,即一跳邻居实体,获得共性邻居感知编码;接着提出一个任务相关实体编码器,挖掘任务实体上下文与共性上下文的相似度信息,区分一跳邻居对当前任务的贡献,增强实体表征;然后提出一个上下文关系编码器获得动态关系表征;最后通过加权求和综合考虑实体上下文和关系的匹配程度,完成补全。ACMN从实体上下文相似度和关系匹配程度两个方面综合评价查询三元组是否成立,能够在小样本的背景下有效提高预测准确性。在两个公共数据集上和其他8个广泛使用的算法进行比较,ACMN在不同规模的小样本情况下,取得了目前最好的补全结果。

关键词: 知识图谱补全, 小样本学习, 实体上下文, 关系预测, 表示学习

Abstract: The knowledge graph needs to face complicated real world information in construction process,and cannot model all knowledge,so it needs to be completed.Many relations in real knowledge graph often have only few entity pairs for training.Therefore,few-shot knowledge graph completion is a very significant problem.At present,embedding-based methods generally aggregate entity context information through attention mechanism or other methods,and complete knowledge graph by learning relation embeddings.These methods only consider the matching degree at relation level.Although they can predict unknown relations,the result is often not accurate.Therefore,an adaptive context matching network(ACMN) is proposed for few-shot know-ledge graph completion.Firstly,a common-neighbor awareness-encoder is proposed to aggregate the references context,that is,one-hop neighbor entities,and obtain common-neighbor awareness embeddings.Secondly,a task-related entity encoder is proposed to mine the similarity information between task entity context and common context,distinguish the contribution of one-hop neighbors to the current task,and enhance task entity representation.Then a context-relation encoder is proposed to obtain dynamic relation representations.Finally,the matching degree of entity context and relations is comprehensively considered through weighted summation to complete the completion.ACMN comprehensively evaluates whether the query triples are tenable from two aspects of entity context similarity and relations matching,which can effectively improve the prediction accuracy in few-shot scena-rios.Compared with other eight widely used algorithms on the two public data sets,ACMN achieves the best completion results in the case of different few-shot sizes.

Key words: Graph competion, Few-shot learning, Entity context, Relation prediction, Representation learning

中图分类号: 

  • TP181
[1]HANG T T,FENG J,LU J M.Knowledge Graph Construction Techniques:Taxonomy,Survey and Future Directions[J].Computer Science,2021,48(2):175-189.
[2]LIANG H H,GU T L,BIN C Z,et al.Combining User-end and Item-end Knowledge Graph Learning for Personalized Recommendation[J].Computer Science,2021,48(5):109-116.
[3]LIU D,LIAN J,LIU Z,et al.Reinforced anchor knowledgegraph generation for news recommendation reasoning[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.2021:1055-1065.
[4]GUO Q,ZHUANG F,QIN C,et al.A survey on knowledge graph-based recommender systems[J].IEEE Transactions on Knowledge and Data Engineering,2020,34(8):3549-3568.
[5]ZHANG Y,QIAN S S,FANG Q,et al.Multi-Modal Know-ledge-Aware Attention Network for Question Answering[J].Journal of Computer Research and Development,2020,57(5):1037-1045.
[6]BOSSELUT A,LE BRAS R,CHOI Y.Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question Answering[C]//AAAI.2021:4923-4931.
[7]KEJRIWAL M,SZEKELY P.Knowledge graphs for socialgood:An entity-centric search engine for the human trafficking domain [J].IEEE Transactions on Big Data,2017,8(3):592-606.
[8]WANG Y,XU X,HONG Q,et al.Top-k star queries on know-ledge graphs through semantic-aware bounding match scores[J].Knowledge-Based Systems,2021,213:106655.
[9]WANG Q,JI Y,HAO Y,et al.GRL:Knowledge graph completion with GAN-based reinforcement learning[J].Knowledge-Based Systems,2020,209:106421.
[10]SHAO P,ZHANG D,YANG G,et al.Tucker decomposition-based temporal knowledge graph completion[J].Knowledge-Based Systems,2022,238:107841.
[11]FENG J,WEI Q,CUI J,et al.Novel translation knowledgegraph completion model based on 2D convolution[J].Applied Intelligence,2022,52(3):3266-3275.
[12]HUANG J,LU T,ZHU J,et al.Multi-relational knowledgegraph completion method with local information fusion[J].Applied Intelligence,2022,52(7):7985-7994.
[13]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.Lake Tahoe,Nevada,2013:2787-2795.
[14]WANG Z,ZHANG J,FENG J,et al.Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2014.
[15]LIN Y,LIU Z,SUN M,et al.Learning entity and relation embeddings for knowledge graph completion[C]//Twenty-ninth AAAI Conference on Artificial Intelligence.2015.
[16]SUN Z,HUANG J,HU W,et al.Transedge:Translating relation-contextualized embeddings for knowledge graphs[C]//The Semantic Web-ISWC 2019:18th International Semantic Web Conference,Auckland,New Zealand,October 26-30,2019,Proceedings,Part I 18.Springer International Publishing,2019:612-629.
[17]XIONG W,YU M,CHANG S,et al.One-Shot Relational Lear-ning for Knowledge Graphs[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.2018:1980-1990.
[18]ZHANG C,YAO H,HUANG C,et al.Few-shot knowledgegraph completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020,34(3):3041-3048.
[19]MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed representations of words and phrases and their compositionality [C]//Proceedings of the 26th International Conference on Neural Information Processing Systems.Lake Tahoe,Nevada,2013:3111-3119.
[20]NICKEL M,TRESP V,KRIEGEL H P.A three-way model for collective learning on multi-relational data [C]//Proceedings of the 28th International Conference on Machine Learning.2011:809-816.
[21]TROUILLON T,WELBL J,RIEDEL S,et al.Complex embeddings for simple link prediction[C]//International Conference on Machine Learning.PMLR,2016:2071-2080.
[22]SOCHER R,CHEN D,MANNING C D,et al.Reasoning with neural tensor networks for knowledge base completion[C]//27th Annual Conference on Neural Information Processing Systems 2013.2013:926-934.
[23]DETTMERS T,MINERVINI P,STENETORP P,et al.Convolutional 2D knowledge graph embeddings [C]//Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence.2018:1811-1818.
[24]SCHLICHTKRULL M,KIPF T N,BLOEM P,et al.Modeling relational data with graph convolutional networks[C]//The Semantic Web:15th International Conference,ESWC 2018,Heraklion,Crete,Greece,June 3-7,2018,Proceedings 15.Springer International Publishing,2018:593-607.
[25]WANG W J,YU Y F.Automatic completion algorithm formissing links in nowledge graph considering data sparsity[J].Journal of Jilin University(Engineering and Technology Edition),2022,52(06):1428-1433.
[26]WANG Y,YAO Q,KWOK J T,et al.Generalizing from a few examples:A survey on few-shot learning[J].ACM Computing Surveys(CSUR),2020,53(3):1-34.
[27]SUNG F,YANG Y,ZHANG L,et al.Learning to compare:Relation network for few-shot learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:1199-1208.
[28]VARTAK M,THIAGARAJAN A,MIRANDA C,et al.A meta-learning perspective on cold-start recommendations for items[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:6907-6917.
[29]GENG R,LI B,LI Y,et al.Induction Networks for Few-ShotText Classification[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP).2019:3904-3913.
[30]DONG X,ZHU L,ZHANG D,et al.Fast parameter adaptation for few-shot image captioning and visual question answering[C]//Proceedings of the 26th ACM International Conference on Multimedia.2018:54-62.
[31]KOCH G,ZEMEL R,SALAKUTDINOV R.Siamese neuralnetworks for one-shot image recognition[C]//ICML& Deep Learning Workshop.2015.
[32]VINYALS O,BLUNDELL C,LILLICRAP T,et al.Matchingnetworks for one shot learning[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems.2016:3637-3645.
[33]SNELL J,SWERSKY K,ZEMEL R.Prototypical networks for few-shot learning[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:4080-4090.
[34]FINN C,ABBEEL P,LEVINE S.Model-agnostic meta-learning for fast adaptation of deep networks[C]//International Confe-rence on Machine Learning.PMLR,2017:1126-1135.
[35]NICHOL A,ACHIAM J,SCHULMAN J.On first-order meta-learning algorithms[J].arXiv:1803.02999,2018.
[36]BANSAL T,JHA R,MCCALLUM A.Learning to Few-ShotLearn Across Diverse Natural Language Classification Tasks[C]//Proceedings of the 28th International Conference on Computational Linguistics.2020:5108-5123.
[37]XIANG J,MOHAMMAD H,GABRIEL C,et al.Attentive task-agnostic meta-learning for few-shot text classifification[C]//Conference on Neural Information Processing Systems & Meta-Learning Workshop.2018.
[38]ASHISH V,NOAM S,NIKI P,et al.Attention is all you need[C]//Neural Information Processing Systems.2017:5998-6008.
[39]CARLSON A,BETTERIDGE J,KISIEL B,et al.Toward an architecture for never-ending language learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2010,24(1):1306-1313.
[40]VRANDEĆIČ D,KRÖTZSCH M.Wikidata:a free collaborative knowledgebase[J].Communications of the ACM,2014,57(10):78-85.
[41]YANG B,YIH S W,HE X,et al.Embedding Entities and Relations for Learning and Inference in Knowledge Bases[C]//Proceedings of the International Conference on Learning Representations.ICLR,2015.
[42]KAZEMI S M,POOLE D.Simple embedding for link predictionin knowledge graphs[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems.2018:4289-4300.
[43]SUN Z Q,DENG Z H,NIE J Y,et al.Rotate:Knowledge graphembeddingby relational rotation in complex space[C]//7th International Conference on Learning Representations.2019:6-9.
[44]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 Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP).2019:4217-4226.
[45]HAN X,CAO S,LV X,et al.Openke:An open toolkit for knowledge embedding[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing:System Demonstrations.2018:139-144.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路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