Abstract
Knowledge graphs can provide a rich resource for constructing question answering systems and recommendation systems. However, most knowledge graphs still encounter knowledge incompleteness. The path-based approach predicts the unknown relation between pairwise entities based on existing path facts. This approach is one of the most promising approaches for knowledge graph completion. A critical challenge of such approaches is integrating path sequence information to achieve the goal of better reasoning. Existing researches focus more on the features between neighboring entities and relations in a path, ignoring the semantic relations of the whole triple. A single path consists of entities and relations, but triples contain valuable semantic information. Moreover, the importance of different triples on each path is disparate. To address these problems, we propose a method convolutional network with hierarchical attention to complete the knowledge graph. Firstly, we use a convolutional network and bidirectional long short-term memory to extract the features of each triple in the path. Then, we employ a novel hierarchical attention network, including triple-level attention and path-level attention, picking up path features at multiple granularities. In addition, we elaborate a multistep reasoning component that repeats multiple interactions with the hierarchical attention module to obtain more plausible inference evidence. Finally, we predict the relation between query entities and provide the most dominant path to explain our answer. The experimental results show that our method outperforms existing approaches by 1–3\(\%\) on four datasets.
Similar content being viewed by others
References
Suchanek FM, Kasneci G, Weikum G (2007) Yago: a core of semantic knowledge. In: Proceedings of the 16th international conference on world wide web, pp 697–706
Auer S, Bizer C, Kobilarov G, Lehmann J, Cyganiak R, Ives Z (2007) Dbpedia: a nucleus for a web of open data. In: Proceedings of the 6th international the semantic web and 2nd Asian conference on Asian semantic web conference, 2007, pp 722–735
Miller GA (1995) Wordnet: a lexical database for english. Commun Acm 38(11):39–41
Bollacker K, Evans C, Paritosh P, Sturge T, Taylor J (2008) Freebase: a collaboratively created graph database for structuring human knowledge. In: Proceedings of the 2008 ACM SIGMOD international conference on management of data, pp 1247–1250
Xiong W, Yu M, Chang S, Guo X, Wang WY (2019) Improving question answering over incomplete KBs with knowledge-aware reader. In: Proceedings of the 57th annual meeting of the association for computational linguistics, pp 4258–4264
Fararni KA, Nafis F, Aghoutane B, Yahyaouy A, Riffi J, Sabri A (2021) Hybrid recommender system for tourism based on big data and ai: a conceptual framework, no 1, p 9
Zhang D, Jia Q, Yang S, Han X, Xu C, Liu X, Xie Y (2022) Traditional Chinese medicine automated diagnosis based on knowledge graph reasoning. CMC Comput Mater Continua 71(1):159–170
Nie K, Zeng K, Meng Q (2020) Knowledge reasoning method for military decision support knowledge graph mixing rule and graph neural networks learning together. In: (2020) Chinese automation congress (CAC). IEEE 2020, pp 4013–4018
Bordes A, Usunier N, Garcia-Durán A, Weston J, Yakhnenko O (2013) Translating embeddings for modeling multi-relational data, 2013, pp 2787–2795
Wang Z, Zhang J, Feng J, Chen Z (2014) Knowledge graph embedding by translating on hyperplanes. In: Proceedings of the AAAI conference on artificial intelligence, vol 28, no 1, pp 1112–1119
Yang B, Yih W-t, He X, Gao J, Deng L (2014) Embedding entities and relations for learning and inference in knowledge bases. arXiv:1412.6575
Lin Y, Liu Z, Luan H, Sun M, Rao S, Liu S (2015) Modeling relation paths for representation learning of knowledge bases
Nickel M, Tresp V, Kriegel H-P (2011) A three-way model for collective learning on multi-relational data. In: Proceedings of the 28th international conference on international conference on machine learning, 2011, pp 809–816
Trouillon T, Welbl J, Riedel S, Gaussier éric, Bouchard G (2016) Complex embeddings for simple link prediction, pp 2071–2080
Dettmers T, Minervini P, Stenetorp P, Riedel S (2018) Convolutional 2d knowledge graph embeddings, pp 1811–1818
Balažević I, Allen C, Hospedales TM (2019) Hypernetwork knowledge graph embeddings. In: International conference on artificial neural networks, 2019, pp 553–565
Sun Z, Deng Z-H, Nie J-Y, Tang J (2019) Rotate: knowledge graph embedding by relational rotation in complex space. In: International conference on learning representations
Lao N, Cohen WW (2010) Relational retrieval using a combination of path-constrained random walks. Mach Learn 81(1):53–67
Wang Q, Liu J, Luo Y, Wang B, Lin C-Y (2016) Knowledge base completion via coupled path ranking. In: Meeting of the association for computational linguistics, pp 1308–1318
Lin Y, Liu Z, Luan H, Sun M, Rao S, Liu S (2015) Modeling relation paths for representation learning of knowledge bases. Comput Sci 705–714
Neelakantan A, Roth B, McCallum A (2015) Compositional vector space models for knowledge base completion, pp 156–166
Das R, Neelakantan A, Belanger D, Mccallum A (2017) Chains of reasoning over entities, relations, and text using recurrent neural networks. arXiv:1607.01426, pp 132–141
(2020) Path-based reasoning approach for knowledge graph completion using cnn-bilstm with attention mechanism. Expert Syst Appl 142
Xiong W, Hoang T, Wang WY (2017) Deeppath: a reinforcement learning method for knowledge graph reasoning, pp 564–573
Das R, Dhuliawala S, Zaheer M, Vilnis L, Durugkar I, Krishnamurthy A, Smola A, McCallum A (2018) Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning. In: International conference on learning representations
Li S, Wang H, Pan R, Mao M (2021) Memorypath: a deep reinforcement learning framework for incorporating memory component into knowledge graph reasoning. Neurocomputing 419:273–286
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998–6008
Yang Z, Yang D, Dyer C, He X, Smola A, Hovy E (2016) Hierarchical attention networks for document classification. NAACL 2016:1480–1489
Shen Y, Ding N, Zheng H-T, Li Y, Yang M (2020) Modeling relation paths for knowledge graph completion. IEEE Trans Knowl Data Eng 33(11):3607–3617
Li C, Peng X, Zhang S, Peng H, Philip SY, He M, Du L, Wang L (2020) Modeling relation paths for knowledge base completion via joint adversarial training. Knowl Based Syst 201:105865
Wang Y, Xiao W, Tan Z, Zhao X (2021) Caps-owkg: a capsule network model for open-world knowledge graph. Int J Mach Learn Cybern 12(6):1627–1637
Ma T, Lv S, Huang L, Hu S (2021) Hiam: a hierarchical attention based model for knowledge graph multi-hop reasoning. Neural Netw
Gan Z, Cheng Y, Kholy AE, Li L, Liu J, Gao J (2019) Multi-step reasoning via recurrent dual attention for visual dialog. arXiv:1902.00579
Sukhbaatar S, Weston J, Fergus R et al (2015) End-to-end memory networks. Advances in neural information processing systems, vol 28
Kingma D, Ba J (2014) Adam: a method for stochastic optimization. Comput Sci
Toutanova K, Chen D (2015) Observed versus latent features for knowledge base and text inference. In: Proceedings of the 3rd workshop on continuous vector space models and their compositionality, pp 57–66
Mitchell T, Cohen W, Hruschka E, Talukdar P, Yang B, Betteridge J, Carlson A, Dalvi B, Gardner M, Kisiel B et al (2018) Never-ending learning, vol 61, no 5, pp 103–115
Bahdanau D, Cho K, Bengio Y (2016) Neural machine translation by jointly learning to align and translate
Kok S, Domingos P (2007) Statistical predicate invention. Association for Computing Machinery, 2007, pp 433–440
Zhang Y, Yao Q, Shao Y, Chen L (2019) Nscaching: simple and efficient negative sampling for knowledge graph embedding. In: 2019 IEEE 35th international conference on data engineering (ICDE). IEEE, 2019, pp 614–625
Gu W, Gao F, Li R, Zhang J (2021) Learning universal network representation via link prediction by graph convolutional neural network. Soc Comput 2(1):9
Ma G, Yan H, Qian Y, Wang L, Zhao Z (2021) Path-based estimation for link prediction. Int J Mach Learn Cybern 3
Funding
This paper supported by Shanxi Province key technology and generic technology R &D project (2020XXX007); National Natural Science Foundation of China (62002255); National Major Scientific Research Instrument Development Project (62027819); The General Object of National Natural Science Foundation(62076177); Graduate Education Innovation Project of Shanxi Province (2021Y199).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
(Check journal-specific guidelines for which heading to use) No conflict of interest
Consent for publication
Yes.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, D., Miao, S., Zhao, B. et al. ConvHiA: convolutional network with hierarchical attention for knowledge graph multi-hop reasoning. Int. J. Mach. Learn. & Cyber. 14, 2301–2315 (2023). https://doi.org/10.1007/s13042-022-01764-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-022-01764-8