Adversarial negative sample generation for knowledge representation learning

doi:10.11772/j.issn.1001-9081.2019020357

Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (9): 2489-2493.DOI: 10.11772/j.issn.1001-9081.2019020357

• Artificial intelligence • Next Articles

Adversarial negative sample generation for knowledge representation learning

ZHANG Zhao, JI Jianmin, CHEN Xiaoping

School of Computer Science and Technology, University of Science and Technology of China, Hefei Anhui 230027, China

Received:2019-03-06 Revised:2019-04-20 Online:2019-09-10 Published:2019-05-14
Supported by:
This work is partially supported by the National Natural Science Foundation of China (U1613216, 61573386), the Science and Technology Planning Project of Guangdong Province (2017B010110011).

用于知识表示学习的对抗式负样本生成

张钊, 吉建民, 陈小平

中国科学技术大学计算机科学与技术学院, 合肥 230027

通讯作者: 吉建民
作者简介:张钊(1994-),男,河北衡水人,硕士研究生,主要研究方向:知识表示学习、知识图谱、自然语言处理;吉建民(1984-),男,甘肃定西人,副教授,博士,CCF会员,主要研究方向:认知机器人、知识表示与推理;陈小平(1955-),男,北京人,教授,博士生导师,博士,主要研究方向:人工智能逻辑、多智能体系统、智能机器人。
基金资助:
国家自然科学基金资助项目（U1613216，61573386）；广东省科技计划项目（2017B010110011）。

Abstract

Abstract:

Knowledge graph embedding is to embed symbolic relations and entities of the knowledge graph into low dimensional continuous vector space. Despite the requirement of negative samples for training knowledge graph embedding models, only positive examples are stored in the form of triplets in most knowledge graphs. Moreover, negative samples generated by negative sampling of conventional knowledge graph embedding methods are easy to be discriminated by the model and contribute less and less as the training going on. To address this problem, an Adversarial Negative Generator (ANG) model was proposed. The generator applied the encoder-decoder pipeline, the encoder readed in positive triplets whose head or tail entities were replaced as context information, and then the decoder filled the replaced entity with the triplet using the encoding information provided by the encoder, so as to generate negative samples. Several existing knowledge graph embedding models were used to play an adversarial game with the proposed generator to optimize the knowledge representation vectors. By comparing with existing knowledge graph embedding models, it can be seen that the proposed method has better mean ranking of link prediction and more accurate triple classification result on FB15K237, WN18 and WN18RR datasets.

Key words: knowledge representation learning, knowledge graph, generative adversarial network, deep learning, knowledge graph embedding

摘要：

知识表示学习目的是将知识图谱中符号化表示的关系与实体嵌入到低维连续向量空间。知识表示模型在训练过程中需要大量负样本，但多数知识图谱只以三元组的形式存储正样本。传统知识表示学习方法中通常使用负采样方法，这种方法生成的负样本很容易被模型判别，随着训练的进行对性能提升的贡献也会越来越小。为了解决这个问题，提出了对抗式负样本生成器（ANG）模型。生成器采用编码-解码架构，编码器读入头或尾实体被替换的正样本作为上下文信息，然后解码器利用编码器提供的编码信息为三元组填充被替换的实体，从而构建负样本。训练过程采用已有的知识表示学习模型与生成器进行对抗训练以优化知识表示向量。在链接预测和三元组分类任务上评估了该方法，实验结果表明该方法对已有知识表示学习模型在FB15K237、WN18和WN18RR数据集上的链接预测平均排名与三元组分类准确度都有提升。

关键词: 知识表示学习, 知识图谱, 生成对抗网络, 深度学习, 知识图谱嵌入

CLC Number:

TP391.1

ZHANG Zhao, JI Jianmin, CHEN Xiaoping. Adversarial negative sample generation for knowledge representation learning[J]. Journal of Computer Applications, 2019, 39(9): 2489-2493.

张钊, 吉建民, 陈小平. 用于知识表示学习的对抗式负样本生成[J]. 计算机应用, 2019, 39(9): 2489-2493.

References

[1] MILLER G A. WordNet:a lexical database for English[J]. Communications of the ACM, 1995, 38(11):39-41.
[2] AUER S, BIZER C, KOBILAROV G, et al. DBpedia:a nucleus for a Web of open data[C]//Proceedings of the 2007 International Semantic Web Conference, LNCS 4825. Berlin:Springer, 2007:722-735.
[3] BOLLACKER K, EVANS C, PARITOSH P, et al. Freebase:a collaboratively created graph database for structuring human knowledge[C]//Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data. New York:ACM, 2008:1247-1250.
[4] BORDES A, USUNIER N, GARCIA-DURÁN A, et al. Translating embeddings for modeling multi-relational data[EB/OL].[2019-01-06]. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.447.6132&rep=rep1&type=pdf.
[5] WANG Z, ZHANG J, FENG J, et al. Knowledge graph embedding by translating on hyperplanes[C]//AAAI'14:Proceedings of the 28th AAAI Conference on Artificial Intelligence. Menlo Park, CA:AAAI Press, 2014:1112-1119.
[6] JI G, HE S, XU L, et al. Knowledge graph embedding via dynamic mapping matrix[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics, 2015, 1:687-696.
[7] YANG B, YIH W, HE X, et al. Embedding entities and relations for learning and inference in knowledge bases[EB/OL].[2019-01-06]. https://arxiv.org/pdf/1412.6575.pdf.
[8] TROUILLON T, WELBL J, RIEDEL S, et al. Complex embeddings for simple link prediction[EB/OL].[2019-01-06]. https://arxiv.org/pdf/1606.06357.pdf.
[9] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//NIPS'14:Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge, MA:MIT Press, 2014, 2:2672-2680.
[10] CAI L, WANG W Y. KBGAN:adversarial learning for knowledge graph embeddings[EB/OL].[2019-01-08]. https://arxiv.org/pdf/1711.04071.pdf.
[11] WANG P, LI S, PAN R. Incorporating GAN for negative sampling in knowledge representation learning[EB/OL].[2019-01-08]. https://arxiv.org/pdf/1809.11017.pdf.
[12] TOUTANOVA K, CHEN D. Observed versus latent features for knowledge base and text inference[EB/OL].[2019-01-08]. http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=332E017631F63128927CF06ABF216792?doi=10.1.1.709.9449&rep=rep1&type=pdf.
[13] DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2D knowledge graph embeddings[EB/OL].[2019-01-08]. https://arxiv.org/pdf/1707.01476.pdf.
[14] LIN Y, LIU Z, SUN M, et al. Learning entity and relation embeddings for knowledge graph completion[C]//AAAI'15:Proceedings of the 29th AAAI Conference on Artificial Intelligence. Menlo Park, CA:AAAI Press, 2015:2181-2187.
[15] NICKEL M, TRESP V, KRIEGEL H P. A three-way model for collective learning on multi-relational data[C]//ICML'11:Proceedings of the 28th International Conference on International Conference on Machine Learning. Bellevue, Washington:Omnipress, 2011:809-816.
[16] NICKEL M, ROSASCO L, POGGIO T. Holographic embeddings of knowledge graphs[EB/OL].[2018-12-25]. https://arxiv.org/pdf/1510.04935v2.pdf.
[17] SOCHER R, CHEN D, MANNING C D, et al. Reasoning with neural tensor networks for knowledge base completion[C]//NIPS'13:Proceedings of the 26th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada:Curran Associates, 2013:926-934.
[18] BOSE A J, LING H, CAO Y. Adversarial contrastive estimation[EB/OL].[2019-01-09]. https://arxiv.org/pdf/1805.03642.pdf.
[19] YU L, ZHANG W, WANG J, et al. SeqGAN:sequence generative adversarial nets with policy gradient[EB/OL].[2019-01-09]. https://arxiv.org/pdf/1609.05473.pdf.
[20] WANG J, YU L, ZHANG W, et al. IRGAN:a minimax game for unifying generative and discriminative information retrieval models[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM, 2017:515-524.
[21] FEDUS W, GOODFELLOW I, DAI A M. MaskGAN:better text generation via filling in the_[EB/OL].[2019-01-09]. http://export.arxiv.org/pdf/1801.07736.
[22] SUTTON R S, BARTO A G. Reinforcement learning:an introduction[EB/OL].[2019-01-08]. http://users.umiacs.umd.edu/~hal/courses/2016F_RL/RL9.pdf.
[23] SUTSKEVER I, VINYALS O, LE Q V. Sequence to sequence learning with neural networks[EB/OL].[2019-01-08]. https://arxiv.org/pdf/1409.3215.pdf.
[24] CHO K, van MERRIENBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[EB/OL].[2019-01-08]. https://arxiv.org/pdf/1406.1078.pdf.
[25] SUTTON R S, MCALLESTER D A, SINGH S P, et al. Policy gradient methods for reinforcement learning with function approximation[EB/OL].[2019-01-09]. https://www.docin.com/p-1195188340.html.
[26] WATKINS C J C H. Learning from delayed rewards[D]. Cambridge:King's College, 1989.
[27] KINGMA D P, BA J L. Adam:a method for stochastic optimization[EB/OL].[2019-01-09]. https://arxiv.org/pdf/1412.6980.pdf.
[28] DUCHI J, HAZAN E, SINGER Y. Adaptive subgradient methods for online learning and stochastic optimization[J]. Journal of Machine Learning Research, 2011, 12:2121-2159.
[29] HAN X, CAO S, LV X, et al. OpenKE:an open toolkit for knowledge embedding[EB/OL].[2019-01-09]. http://nlp.csai.tsinghua.edu.cn/~lzy/publications/emnlp2018_openke.pdf.

Adversarial negative sample generation for knowledge representation learning

用于知识表示学习的对抗式负样本生成

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	ZHENG Zhiqiang, HU Xin, WENG Zhi, WANG Yuhe, CHENG Xi. Cattle eye image feature extraction method based on improved DenseNet [J]. Journal of Computer Applications, 2021, 41(9): 2780-2784.
[2]	XIE Defeng, JI Jianmin. Syntax-enhanced semantic parsing with syntax-aware representation [J]. Journal of Computer Applications, 2021, 41(9): 2489-2495.
[3]	DAI Yurou, YANG Qing, ZHANG Fengli, ZHOU Fan. Trajectory prediction model of social network users based on self-supervised learning [J]. Journal of Computer Applications, 2021, 41(9): 2545-2551.
[4]	LIU Yaxuan, ZHONG Yong. Joint extraction method of entities and relations based on subject attention [J]. Journal of Computer Applications, 2021, 41(9): 2517-2522.
[5]	CHEN Chengrui, SUN Ning, HE Shibiao, LIAO Yong. Deep learning-based joint channel estimation and equalization algorithm for C-V2X communications [J]. Journal of Computer Applications, 2021, 41(9): 2687-2693.
[6]	YU Dunhui, WAN Peng, WANG She. Entity association query system based on enterprise knowledge graph construction [J]. Journal of Computer Applications, 2021, 41(9): 2510-2516.
[7]	ZHAO Hong, KONG Dongyi. Chinese description of image content based on fusion of image feature attention and adaptive attention [J]. Journal of Computer Applications, 2021, 41(9): 2496-2503.
[8]	XU Jianglang, LI Linyan, WAN Xinjun, HU Fuyuan. Indoor scene recognition method combined with object detection [J]. Journal of Computer Applications, 2021, 41(9): 2720-2725.
[9]	GUAN Qijie, ZHANG Ting, LI Deya, ZHOU Shaojing, DU Yi. Indefinite reconstruction method of spatial data based on multi-resolution generative adversarial network [J]. Journal of Computer Applications, 2021, 41(8): 2306-2311.
[10]	SUN Xiao, XU Jindong. Remote sensing image dehazing method based on cascaded generative adversarial network [J]. Journal of Computer Applications, 2021, 41(8): 2440-2444.
[11]	HE Zhenghai, XIAN Yantuan, WANG Meng, YU Zhengtao. Case reading comprehension method combining syntactic guidance and character attention mechanism [J]. Journal of Computer Applications, 2021, 41(8): 2427-2431.
[12]	TIAN Ling, ZHANG Jinchuan, ZHANG Jinhao, ZHOU Wangtao, ZHOU Xue. Knowledge graph survey： representation， construction， reasoning and knowledge hypergraph theory [J]. Journal of Computer Applications, 2021, 41(8): 2161-2186.
[13]	CAO Yuhong, XU Hai, LIU Sun'ao, WANG Zixiao, LI Hongliang. Review of deep learning-based medical image segmentation [J]. Journal of Computer Applications, 2021, 41(8): 2273-2287.
[14]	QIN Binbin, PENG Liangkang, LU Xiangming, QIAN Jiangbo. Research progress on driver distracted driving detection [J]. Journal of Computer Applications, 2021, 41(8): 2330-2337.
[15]	TANG Guihua, SUN Lei, MAO Xiuqing, DAI Leyu, HU Yongjin. Generative adversarial network synthesized face detection based on deep alignment network [J]. Journal of Computer Applications, 2021, 41(7): 1922-1927.