Volume 30 Issue 4
Jul.  2021
Turn off MathJax
Article Contents
TANG Caifang, RAO Yuan, YU Hualei, et al., “Improving Knowledge Graph Completion Using Soft Rules and Adversarial Learning,” Chinese Journal of Electronics, vol. 30, no. 4, pp. 623-633, 2021, doi: 10.1049/cje.2021.05.004
Citation: TANG Caifang, RAO Yuan, YU Hualei, et al., “Improving Knowledge Graph Completion Using Soft Rules and Adversarial Learning,” Chinese Journal of Electronics, vol. 30, no. 4, pp. 623-633, 2021, doi: 10.1049/cje.2021.05.004

Improving Knowledge Graph Completion Using Soft Rules and Adversarial Learning

doi: 10.1049/cje.2021.05.004
Funds:

The research work is supported by National Key Research and Development Program in China (No.2019YFB2102300), the World-Class Universities (Disciplines) and the Characteristic Development Guidance Funds for the Central Universities of China (No.PY3A022), Ministry of Education Fund Projects (No.18JZD022, No.2017B00030)

Shenzhen Science and Technology Project (No.JCYJ20180306170836595), Basic Scientific Research Operating Expenses of Central Universities (No.ZDYF2017006), Xi’an Navinfo Corp.& Engineering Center of Xi’an Intelligence Spatial-temporal Data Analysis Project (No.C2020103), and Beilin District of Xi’an Science & Technology Project (No.GX1803).

  • Received Date: 2019-07-22
    Available Online: 2021-07-19
  • Publish Date: 2021-07-05
  • Knowledge graph is a useful resources and tools for describing entities and relationships in natural language processing tasks. However, the existing knowledge graph are incomplete. Therefore, knowledge graph completion technology has become a research hotspot in the field of artificial intelligence, but the traditional knowledge graph embedding method does not fully take into account the role of logic rules and the effect of false negative samples on knowledge embedding. Based on the logic rules of knowledge and the role of adversarial learning in knowledge embedding, we proposes a model to improve the completion of knowledge graph: soft Rules and graph adversarial learning (RUGA). Firstly, the traditional knowledge graph embedding model is trained as generator and discriminator by using adversarial learning method, and high-quality negative samples are obtained. Then these negative samples and the existing positive samples together constitute the label triple in the injection rule model. The whole model will benefit from both high-quality samples and logical rules. In addition, we evaluated the performance of link prediction task and triple classification task on Freebase and Yago datasets respectively. Finally, the experimental results show that the model can effectively improve the effect of knowledge graph completion.
  • loading
  • AMIT S, "Introducing the knowledge graph", America:Official Blog of Google, 2012.
    Bollacker K D, Evans C, Paritosh P, et al., "Freebase:A collaboratively created graph database for structuring human knowledge", Proc. of the ACM SIGMOD International Conference on Management of Data, Vancouver, BC, Canada, pp.1247-1250, 2008.
    Robert West, Evgeniy Gabrilovich, Kevin Murphy, et al., "Knowledge base completion via searchbased question answering", Proc. of the 23rd International Conference on World Wide Web, pp.515-526, 2014.
    Auer S, Bizer C, Kobilarov G, et al., "DBpedia:A nucleus for a web of open data" The Semantic Web, 6th International Semantic Web Conference, 2nd Asian Semantic Web Conference, Busan, Korea, pp.722-735, 2007.
    Denis Krompaß, Stephan Baier, and Volker Tresp, et al.,"Type-constrained representation learning in knowledge graphs", Proc. of the 14th International Semantic Web Conference, pp.640-655, 2015.
    Mikolov T, Sutskever I, Chen K, et al., "Distributed representations of words and phrases and their compositionality", Proc. of the 23rd International Conference on World Wide Web, Vol.26, pp.3111-3119, 2013.
    Mikolov T, Chen K, Corrado G, et al., "Efficient estimation of word representations in vector space", available at https://arxiv.org/abs/1301.3781,2013-9-7.
    Bordes A, Usunier N, Garcia-duran A, et al., "Translating embeddings for modeling multi-relational data", Proc. of the Conference and Workshop on Neural Information Processing Systems, Cambridge, MA:MIT Press, pp.2787-2795, 2013.
    Wang Z, Zhang J, Feng J, et al., "Knowledge graph embedding by translating on hyperplanes", Proc. of the Association for the Advance of Artificial Intelligence, Menlo Park, CA, pp.1112-1119, 2014.
    Lin Y, Liu Z, Zhu X, et al., "Learning entity and relation embeddings for knowledge graph completion", Proc. of the Association for the Advance of Artificial Intelligence, CA, pp.2181-2187, 2015.
    Guoliang Ji, Shizhu He, Liheng Xu, et al., "Knowledge graph embedding via dynamic graphping matrix", Proc. of the 53rd Annual Meeting of the Association for Computational Linguistics, pp.689-696, 2015.
    Trouillon T, Welbl J, Riedel S, et al., "Complex Embeddings for Simple Link Prediction", Proc. of the 54rd Annual Meeting of the Association for Computational Linguistics, pp.2071-2080, 2016.
    Guo, S., Wang, Q, Wang L, et al., "Jointly embedding knowledge graphs and logical rules", Proc. of the Conference on Empirical Methods in Natural Language Processing, pp.192-202, 2016.
    Shu Guo, Quan Wang, Lihong Wang,et al., "Knowledge graph embedding with iterative guidance from soft rules", https://arxiv.org/abs/1711.11231, 2017-11-30.
    Zhen Wang, Jianwen Zhang, Jianlin Feng, et al., "Knowledge graph embedding bytranslating on hyperplanes", Proc. of the Twenty-eighth AAAI Conference on Artificial Intelligence, pp.1112-1119, 2014.
    Cai L, Wang W Y, "Adversarial learning for knowledge graph embeddings", https://arxiv.org/pdf/1711.04071.pdf, 2018-5-11.
    Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, et al.,"Generative adversarial nets", Proc. of the Neural Information Processing Systems, pp.2672-2680, 2014.
    Bishan Yang, Wen-tau Yih, Xiaodong He, et al., "Embedding entities and relations for learning and inference in knowledge bases", https://arxiv.org/abs/1412.6575, 2015-8-29.
    Pelletier,F.J,"Metamathematics of fuzzy logic", Proc. of the Bulletin of Symbolic Logic, Vol.6, No.3, pp.342-346, 2000.
    Tomas Mikolov, Ilya Sutskever, Kai Chen, et al., "Distributed representations of words and phrases and their compositionality", in Advances in Neural Information Processing Systems, pp.3111-3119, 2013.
    Richard S Sutton, David A McAllester, Satinder PSingh, et al., "Policy gra-dient methods for reinforcement learning with function approximation", in Advances in Neural Information Processing Systems, pp.1057-1063, 2000.
    Nickel M, Rosasco L and Poggio T, "Holographic embeddings of knowledge graphs", Proc. of the Association for the Advance of Artificial Intelligence, pp.1955-1961, 2016.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (661) PDF downloads(39) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return