skip to main content
research-article

One-Shot Relation Learning for Knowledge Graphs via Neighborhood Aggregation and Paths Encoding

Authors Info & Claims
Published:13 December 2021Publication History
Skip Abstract Section

Abstract

The relation learning between two entities is an essential task in knowledge graph (KG) completion that has received much attention recently. Previous work almost exclusively focused on relations widely seen in the original KGs, which means that enough training data are available for modeling. However, long-tail relations that only show in a few triples are actually much more common in practical KGs. Without sufficiently large training data, the performance of existing models on predicting long-tail relations drops impressively. This work aims to predict the relation under a challenging setting where only one instance is available for training. We propose a path-based one-shot relation prediction framework, which can extract neighborhood information of an entity based on the relation query attention mechanism to learn transferable knowledge among the same relation. Simultaneously, to reduce the impact of long-tail entities on relation prediction, we selectively fuse path information between entity pairs as auxiliary information of relation features. Experiments in three one-shot relation learning datasets show that our proposed framework substantially outperforms existing models on one-shot link prediction and relation prediction.

REFERENCES

  1. [1] Auer Sören, Bizer Christian, Kobilarov Georgi, Lehmann Jens, Cyganiak Richard, and Ives Zachary. 2007. DBpedia: A nucleus for a web of open data. In The Semantic Web. Springer, Berlin, Germany, 722735. Google ScholarGoogle ScholarDigital LibraryDigital Library
  2. [2] Balažević Ivana, Allen Carl, and Hospedales Timothy M.. 2019. TuckER: Tensor factorization for knowledge graph completion. arXiv preprint arXiv:1901.09590 (2019).Google ScholarGoogle Scholar
  3. [3] Bordes Antoine, Usunier Nicolas, Garcia-Duran Alberto, Weston Jason, and Yakhnenko Oksana. 2013. Translating embeddings for modeling multi-relational data. In Advances in Neural Information Processing Systems 26. Curran Associates, 27872795. http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf. Google ScholarGoogle ScholarDigital LibraryDigital Library
  4. [4] Chen Mingyang, Zhang Wen, Zhang Wei, Chen Qiang, and Chen Huajun. 2019. Meta relational learning for few-shot link prediction in knowledge graphs. arXiv preprint arXiv:1909.01515 (2019).Google ScholarGoogle Scholar
  5. [5] Das Rajarshi, Neelakantan Arvind, Belanger David, and McCallum Andrew. 2017. Chains of reasoning over entities, relations, and text using recurrent neural networks. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. 132141. https://www.aclweb.org/anthology/E17-1013.Google ScholarGoogle ScholarCross RefCross Ref
  6. [6] Du Zhengxiao, Zhou Chang, Ding Ming, Yang Hongxia, and Tang Jie. 2019. Cognitive knowledge graph reasoning for one-shot relational learning. CoRR abs/1906.05489 (2019). arXiv:1906.05489 http://arxiv.org/abs/1906.05489.Google ScholarGoogle Scholar
  7. [7] Finn Chelsea, Abbeel Pieter, and Levine Sergey. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. CoRR abs/1703.03400 (2017). arXiv:1703.03400 http://arxiv.org/abs/1703.03400. Google ScholarGoogle ScholarDigital LibraryDigital Library
  8. [8] Gao Tianyu, Han Xu, Liu Zhiyuan, and Sun Maosong. 2019. Hybrid attention-based prototypical networks for noisy few-shot relation classification. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI’19). Google ScholarGoogle ScholarDigital LibraryDigital Library
  9. [9] Gao Tianyu, Han Xu, Xie Ruobing, Liu Zhiyuan, Lin Fen, Lin Leyu, and Sun Maosong. 2019. Neural snowball for few-shot relation learning. ArXiv abs/1908.11007 (2019).Google ScholarGoogle Scholar
  10. [10] Han Xu, Zhu Hao, Yu Pengfei, Wang Ziyun, Yao Yuan, Liu Zhiyuan, and Sun Maosong. 2018. FewRel: A large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 48034809. DOI: DOI: https://doi.org/10.18653/v1/D18-1514Google ScholarGoogle ScholarCross RefCross Ref
  11. [11] Kingma Diederik P. and Ba Jimmy. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google ScholarGoogle Scholar
  12. [12] Koch Gregory, Zemel Richard, and Salakhutdinov Ruslan. 2015. Siamese neural networks for one-shot image recognition. In ICML Deep Learning Workshop, vol. 2.Google ScholarGoogle Scholar
  13. [13] Lao Ni and Cohen William W.. 2010. Relational retrieval using a combination of path-constrained random walks. Machine Learning 81, 1 (2010), 5367. Google ScholarGoogle ScholarDigital LibraryDigital Library
  14. [14] Li J., Chiu B., Feng S., and Wang H.. 2020. Few-shot named entity recognition via meta-learning. IEEE Transactions on Knowledge and Data Engineering. Early access, November 17, 2020. DOI: DOI: https://doi.org/10.1109/TKDE.2020.3038670Google ScholarGoogle ScholarCross RefCross Ref
  15. [15] Li Zhenguo, Zhou Fengwei, Chen Fei, and Li Hang. 2017. Meta-SGD: Learning to learn quickly for few shot learning. CoRR abs/1707.09835 (2017). arXiv:1707.09835 http://arxiv.org/abs/1707.09835.Google ScholarGoogle Scholar
  16. [16] Lv Xin, Gu Yuxian, Han Xu, Hou Lei, Li Juanzi, and Liu Zhiyuan. 2019. Adapting meta knowledge graph information for multi-hop reasoning over few-shot relations. arXiv preprint arXiv:1908.11513 (2019).Google ScholarGoogle Scholar
  17. [17] Mahdisoltani Farzaneh, Biega Joanna, and Suchanek Fabian M.. 2015. YAGO3: A knowledge base from multilingual Wikipedias. In Proceedings of the 7th Biennial Conference on Innovative Data Systems Research (CIDR’15).Google ScholarGoogle Scholar
  18. [18] Mitchell T., Cohen W., Hruschka E., Talukdar P., Yang B., Betteridge J., Carlson A., et al. 2018. Never-ending learning. Communications of the ACM 61, 5 (April 2018), 103115. DOI: DOI: https://doi.org/10.1145/3191513 Google ScholarGoogle ScholarCross RefCross Ref
  19. [19] Neelakantan Arvind, Roth Benjamin, and McCallum Andrew. 2015. Compositional vector space models for knowledge base completion. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 156166. DOI: DOI: https://doi.org/10.3115/v1/P15-1016Google ScholarGoogle ScholarCross RefCross Ref
  20. [20] Nickel Maximilian, Tresp Volker, and Kriegel Hans-Peter. 2011. A three-way model for collective learning on multi-relational data. In Proceedings of the 28th International Conference on Machine Learning (ICML’11). 809816. Google ScholarGoogle ScholarDigital LibraryDigital Library
  21. [21] Qu Meng, Gao Tianyu, Xhonneux Louis-Pascal, and Tang Jian. 2020. Few-shot relation extraction via Bayesian meta-learning on relation graphs. In Proceedings of the International Conference on Machine Learning. 78677876.Google ScholarGoogle Scholar
  22. [22] Ravi Sachin and Larochelle Hugo. 2017. Optimization as a model for few-shot learning. In Proceedings of the International Conference on Learning Representations.Google ScholarGoogle Scholar
  23. [23] Santoro Adam, Bartunov Sergey, Botvinick Matthew, Wierstra Daan, and Lillicrap Timothy. 2016. One-shot learning with memory-augmented neural networks. arXiv preprint arXiv:1605.06065 (2016).Google ScholarGoogle Scholar
  24. [24] Sheng Jiawei, Guo Shu, Chen Zhenyu, Yue Juwei, Wang Lihong, Liu Tingwen, and Xu Hongbo. 2020. Adaptive attentional network for few-shot knowledge graph completion. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 16811691. DOI: DOI: https://doi.org/10.18653/v1/2020.emnlp-main.131Google ScholarGoogle ScholarCross RefCross Ref
  25. [25] Snell Jake, Swersky Kevin, and Zemel Richard. 2017. Prototypical networks for few-shot learning. In Advances in Neural Information Processing Systems. 40774087. Google ScholarGoogle ScholarDigital LibraryDigital Library
  26. [26] Sun Zhiqing, Deng Zhi-Hong, Nie Jian-Yun, and Tang Jian. 2019. RotatE: Knowledge graph embedding by relational rotation in complex space. In Proceedings of the International Conference on Learning Representations. https://openreview.net/forum?id=HkgEQnRqYQ.Google ScholarGoogle Scholar
  27. [27] Sun Zhiqing, Deng Zhi-Hong, Nie Jian-Yun, and Tang Jian. 2019. RotatE: Knowledge graph embedding by relational rotation in complex space. arXiv:1902.10197 (2019).Google ScholarGoogle Scholar
  28. [28] Sung Flood, Yang Yongxin, Zhang Li, Xiang Tao, Torr Philip H. S., and Hospedales Timothy M.. 2018. Learning to compare: Relation network for few-shot learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 11991208.Google ScholarGoogle ScholarCross RefCross Ref
  29. [29] Trouillon Théo, Welbl Johannes, Riedel Sebastian, Gaussier Éric, and Bouchard Guillaume. 2016. Complex embeddings for simple link prediction. In Proceedings of the International Conference on Machine Learning. 20712080. Google ScholarGoogle ScholarDigital LibraryDigital Library
  30. [30] Vinyals Oriol, Blundell Charles, Lillicrap Timothy, Kavukcuoglu Koray, and Wierstra Daan. 2016. Matching networks for one shot learning. In Advances in Neural Information Processing Systems 29. https://proceedings.neurips.cc/paper/2016/file/90e1357833654983612fb05e3ec9148c-Paper.pdf. Google ScholarGoogle ScholarDigital LibraryDigital Library
  31. [31] Vrandecic Denny and Krotzsch Markus. 2014. Wikidata: A free collaborative knowledge base. Communications of the ACM 57 (2014), 7885. http://cacm.acm.org/magazines/2014/10/178785-wikidata/fulltext. Google ScholarGoogle ScholarDigital LibraryDigital Library
  32. [32] Wang Hongwei, Ren Hongyu, and Leskovec Jure. 2020. Entity context and relational paths for knowledge graph completion. arXiv preprint arXiv:2002.06757 (2020).Google ScholarGoogle Scholar
  33. [33] Wang Weikang, Zhang Jiajun, Li Qian, Zong Chengqing, and Li Zhifei. 2019. Are you for real? Detecting identity fraud via dialogue interactions. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP’19). 17621771. DOI: DOI: https://doi.org/10.18653/v1/D19-1185Google ScholarGoogle ScholarCross RefCross Ref
  34. [34] Wang Zhen, Zhang Jianwen, Feng Jianlin, and Chen Zheng. 2014. Knowledge graph embedding by translating on hyperplanes. In Proceedings of the 28th AAAI Conference on Artificial Intelligence. Google ScholarGoogle ScholarDigital LibraryDigital Library
  35. [35] Xiong Wenhan, Yu Mo, Chang Shiyu, Guo Xiaoxiao, and Wang William Yang. 2018. One-shot relational learning for knowledge graphs. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.19801990. https://aclanthology.info/papers/D18-1223/d18-1223.Google ScholarGoogle ScholarCross RefCross Ref
  36. [36] Yan Jinghui, Wang Yining, Xiang Lu, Zhou Yu, and Zong Chengqing. 2020. A knowledge-driven generative model for multi-implication Chinese medical procedure entity normalization. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.Google ScholarGoogle ScholarCross RefCross Ref
  37. [37] Yang Bishan, Yih Wen-Tau, He Xiaodong, Gao Jianfeng, and Deng Li. 2014. Embedding entities and relations for learning and inference in knowledge bases. In Proceedings of the International Conference on Learning Representations.Google ScholarGoogle Scholar
  38. [38] Ye Zhi-Xiu and Ling Zhen-Hua. 2019. Multi-level matching and aggregation network for few-shot relation classification. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2872–2881.Google ScholarGoogle ScholarCross RefCross Ref
  39. [39] Yu Mo, Guo Xiaoxiao, Yi Jinfeng, Chang Shiyu, Potdar Saloni, Cheng Yu, Tesauro Gerald, Wang Haoyu, and Zhou Bowen. 2018. Diverse few-shot text classification with multiple metrics. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 12061215. DOI: DOI: https://doi.org/10.18653/v1/N18-1109Google ScholarGoogle ScholarCross RefCross Ref
  40. [40] Zhang Chuxu, Yao Huaxiu, Huang Chao, Jiang Meng, Li Zhenhui, and Chawla Nitesh V.. 2020. Few-shot knowledge graph completion. Proceedings of the AAAI Conference on Artificial Intelligence 34, 3 (April 2020), 30413048. DOI: DOI: https://doi.org/10.1609/aaai.v34i03.5698Google ScholarGoogle ScholarCross RefCross Ref
  41. [41] Zhang Ningyu, Deng Shumin, Sun Zhanlin, Wang Guanying, Chen Xi, Zhang Wei, and Chen Huajun. 2019. Long-tail relation extraction via knowledge graph embeddings and graph convolution networks. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 30163025. DOI: DOI: https://doi.org/10.18653/v1/N19-1306Google ScholarGoogle ScholarCross RefCross Ref
  42. [42] Zhao Yang, Zhang Jiajun, Zhou Yu, and Zong Chengqing. 2020. Knowledge graphs enhanced neural machine translation. In Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI’20). 40394045. Google ScholarGoogle ScholarDigital LibraryDigital Library
  43. [43] Zong Chengqing, Xia Rui, and Zhang Jiajun. 2021. Text Data Mining. Springer.Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. One-Shot Relation Learning for Knowledge Graphs via Neighborhood Aggregation and Paths Encoding

        Recommendations

        Comments

        Login options

        Check if you have access through your login credentials or your institution to get full access on this article.

        Sign in

        Full Access

        • Published in

          cover image ACM Transactions on Asian and Low-Resource Language Information Processing
          ACM Transactions on Asian and Low-Resource Language Information Processing  Volume 21, Issue 3
          May 2022
          413 pages
          ISSN:2375-4699
          EISSN:2375-4702
          DOI:10.1145/3505182
          Issue’s Table of Contents

          Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

          Publisher

          Association for Computing Machinery

          New York, NY, United States

          Publication History

          • Published: 13 December 2021
          • Accepted: 1 August 2021
          • Revised: 1 July 2021
          • Received: 1 May 2021
          Published in tallip Volume 21, Issue 3

          Permissions

          Request permissions about this article.

          Request Permissions

          Check for updates

          Qualifiers

          • research-article
          • Refereed

        PDF Format

        View or Download as a PDF file.

        PDF

        eReader

        View online with eReader.

        eReader

        Full Text

        View this article in Full Text.

        View Full Text

        HTML Format

        View this article in HTML Format .

        View HTML Format
        About Cookies On This Site

        We use cookies to ensure that we give you the best experience on our website.

        Learn more

        Got it!