Analysis of Knowledge Graph Path Reasoning Based on Variational Reasoning
Abstract
:1. Introduction
- We propose a graph variational reasoning model framework (GraphDIVA), which combines a graph neural network and introduces a pretraining process to improve the reasoning performance of the knowledge graph.
- We introduce the GraphSAGE algorithm into the path reasoning module to generate the path feature matrix, enhance the model’s perception of the graph structure, and improve the accuracy of the model.
- We demonstrate that our method can scale up to large KGs and achieve better results on two popular datasets.
2. Related Work
3. Methods
3.1. DIVA Model
3.2. GraphSAGE Algorithm
3.3. Graph DIVA Model
3.3.1. Path Feature Generation Process
3.3.2. Structure Diagram of Path Reasoning Module
4. Experiments
4.1. Datasets
4.2. Training Environment
4.3. Path Search Module Training
4.4. Accuracy Rate Analysis
4.5. Number of Training Sessions
5. Conclusions and Future Work
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Hogan, A.; Blomqvist, E.; Cochez, M.; D’Amato, C.; de Melo, G.; Gutierrez, C.; Gayo, J.E.L.; Kirrane, S.; Neumaier, S.; Polleres, A.; et al. Knowledge graphs. arXiv 2020, arXiv:2003.02320v3. [Google Scholar]
- Caihua, Y.; Tonghui, K.; Jun, L. knowledge graph analysis of low carbon research in China. Resour. Sci. 2012, 10, 1959–1964. [Google Scholar]
- Xu, Z.; Zhang, H.; Hu, C.; Mei, L.; Xuan, J.; Choo, K.K.R.; Sugumaran, V.; Zhu, Y. Building knowledge base of urban emergency events based on crowdsourcing of social media. Concurr. Comput. Pract. Exp. 2016, 28, 4038–4052. [Google Scholar] [CrossRef]
- Tonghui, K.; Caihua, Y.; Qianjin, Z.; Qinjian, Y. Analysis of knowledge graph of tourism research from 2000 to 2010 based on CSSCI. J. Tour. 2013, 3, 114–119. [Google Scholar]
- Wang, Q.; Mao, Z.; Wang, B.; Guo, L. Knowledge graph embedding: A survey of approaches and applications. IEEE Trans. Knowl. Data Eng. 2017, 29, 2724–2743. [Google Scholar] [CrossRef]
- Kingma, D.P.; Welling, M. Auto-encoding variational bayes. arXiv 2013, arXiv:1312.6114. [Google Scholar]
- Chen, W.; Xiong, W.; Yan, X.; Wang, W. Variational knowledge graph reasoning. arXiv 2018, arXiv:1803.06581. [Google Scholar]
- Lao, N.; Mitchell, T.; Cohen, W. Random walk inference and learning in a large scale knowledge base. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, Edinburgh, UK, 27–31 July 2011; Association for Computational Linguistics: Edinburgh, UK, 2011; pp. 529–539. [Google Scholar]
- Xiong, W.; Hoang, T.; Wang, W.Y. Deeppath: A reinforcement learning method for knowledge graph reasoning. arXiv 2017, arXiv:1707.06690. [Google Scholar]
- Das, R.; Dhuliawala, S.; Zaheer, M.; Vilnis, L.; Durugkar, I.; Krishnamurthy, A.; Smola, A.; McCallum, A. Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning. arXiv 2017, arXiv:1711.05851. [Google Scholar]
- Bordes, A.; Usunier, N.; García-Durán, A.; Weston, J.; Yakhnenko, O. Translating embeddings for modeling multi-relational data. In Proceedings of the 26th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA, 5–10 December 2013; Curran Associates Inc.: Red Hook, NY, USA, 2013; pp. 2787–2795. [Google Scholar]
- Wang, Z.; Zhang, J.; Feng, J.; Chen, Z. Knowledge graph embedding by translating on hyperplanes. In Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, AAAI, Québec City, QC, Canada, 27–31 July 2014; pp. 1112–1119. [Google Scholar]
- Ji, G.; He, S.; Xu, L.; Liu, K.; Zhao, J. Knowledge graph embedding via dynamic mapping matrix. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, Beijing, China, 26–31 July 2015; Association for Computational Linguistics: Beijing, China, 2015; pp. 687–696. [Google Scholar]
- Lin, Y.; Liu, Z.; Sun, M.; Liu, Y.; Zhu, X. Learning entity and relation embeddings for knowledge graph completion. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, Austin, TX, USA, 25–30 January 2015; AAAI Press: Palo Alto, CA, USA, 2015; pp. 2181–2187. [Google Scholar]
- Ji, G.; Liu, K.; He, S.; Zhao, J. Knowledge graph completion with adaptive sparse transfer matrix. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, AAAI, Phoenix, AZ, USA, 12–17 February 2016; pp. 985–991. [Google Scholar]
- Neelakantan, A.; Roth, B.; McCallum, A. Compositional vector space models for knowledge base inference. In AAAI Spring Symposia 2015; AAAI: Palo Alto, CA, USA, 2015; pp. 1–4. [Google Scholar]
- Das, R.; Neelakantan, A.; Belanger, D.; McCallum, A. Chains of reasoning over entities, relations, and text using recurrent neural networks. arXiv 2016, arXiv:1607.01426. [Google Scholar]
- Zhang, Y.; Dai, H.; Kozareva, Z.; Smola, A.J.; Song, L. Variational reasoning for question answering with knowledge graph. In Thirty-Second AAAI Conference on Artificial Intelligence; AAAI Press: New Orleans, LA, USA, 2018; pp. 6069–6076. [Google Scholar]
- Geng, Q.; Zhou, Z.; Cao, X. Survey of recent progress in semantic image segmentation with CNNs. Sci. China Inf. Sci. 2018, 61, 051101. [Google Scholar] [CrossRef] [Green Version]
- Duvenaud, D.; Maclaurin, D.; Aguilera-Iparraguirre, J.; Gómez-Bombarelli, R.; Hirzel, T.; Aspuru-Guzik, A.; Adams, R.P. Convolutional networks on graphs for learning molecular fingerprints. arXiv 2015, arXiv:1509.09292. [Google Scholar]
- Kipf, T.N.; Welling, M. Semi-supervised classification with graph convolutional networks. arXiv 2016, arXiv:1609.02907. [Google Scholar]
- Wang, H.; Lin, H.Z.; Lu, L.Y. Knowledge Map Inference Algorithm Based on AT_GCN Model[J/OL].Computer Engineering and Application:1-8[2019-08-15]. Available online: http://kns.cnki.net/kcms/detail/11.2127.TP.20190719.0943.005.html (accessed on 25 January 2021).
- Peng, Z.; Yu, H.; Jia, X. Path-based reasoning with K-nearest neighbor and position embedding for knowledge graph completion. J. Intell. Inf. Syst. 2021, 58, 513–533. [Google Scholar] [CrossRef]
- Tiwari, P.; Zhu, H.; Pandey, H.M. DAPath: Distance-aware knowledge graph reasoning based on deep reinforcement learning. Neural Netw. 2021, 135, 1–12. [Google Scholar] [CrossRef] [PubMed]
- Wang, Q.; Hao, Y.; Chen, F. Deepening the IDA* algorithm for knowledge graph reasoning through neural network architecture. Neurocomputing 2021, 429, 101–109. [Google Scholar] [CrossRef]
- Liu, H.; Zhou, S.; Chen, C.; Gao, T.; Xu, J.; Shu, M. Dynamic knowledge graph reasoning based on deep reinforcement learning. Knowl.-Based Syst. 2022, 241, 108235. [Google Scholar] [CrossRef]
- Zhang, Y.; Yao, Q. Knowledge graph reasoning with relational digraph. In Proceedings of the ACM Web Conference, Lyon, France, 25–29 April 2022; pp. 912–924. [Google Scholar]
- Zhu, A.; Ouyang, D.; Liang, S.; Shao, J. Step by step: A hierarchical framework for multi-hop knowledge graph reasoning with reinforcement learning. Knowl.-Based Syst. 2022, 248, 108843. [Google Scholar] [CrossRef]
- Hamilton, W.; Ying, R.; Leskovec, J. Inductive representation learning on large graphs. In Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017; pp. 1025–1035. [Google Scholar]
- Połap, D.; Woźniak, M.; Wei, W.; Damaševičius, R. Multi-threaded learning control mechanism for neural networks. Future Gener. Comput. Syst. 2018, 87, 16–34. [Google Scholar] [CrossRef]
- Toutanova, K.; Chen, D.; Pantel, P.; Poon, H.; Choudhury, P.; Gamon, M. Representing text for joint embedding of text and knowledge bases. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal, 17–21 September 2015; Association for Computational Linguistics: Lisbon, Portugal, 2015; pp. 1499–1509. [Google Scholar]
- Betteridge, J.; Carlson, A.; Hong, S.A.; Hruschka, E.R.; Law, E.L.M.; Tom, M.; Wang, S.H. Toward never ending language learning. In Proceedings of the AAAI Spring Symposium: Learning by Reading and Learning to Read, Stanford, CA, USA, 23–25 March 2009; pp. 1–2. [Google Scholar]
- Liu, S.; Xia, Z. A two-stage BFS local community detection algorithm based on node transfer similarity and local clustering coefficient. Phys. A Stat. Mech. Appl. 2020, 537, 122717. [Google Scholar] [CrossRef]
Dataset Name | FB15K-237 1 | NELL-995 2 |
---|---|---|
Number of entities | 14,505 | 75,492 |
Number of relationships | 237 | 200 |
Number of triples | 310,116 | 154,213 |
Task type | 20 | 12 |
Parameter | Value |
---|---|
finder_lstm_width | 200 |
finder_mlp_width | 200 |
reasoner_cnn_filter_size | 64 |
reasoner_aggregate_width | 200 |
reasoner_aggregate_neighbours | 25 |
reasoner_lstm_width | 200 |
reasoner_mlp_width | 200 |
Parameter | Value |
---|---|
guided_learn_rate | 0.001 |
guided_max_epoch | 25 |
guided_max_path_width | 5 |
unified_max_epoch | 20 |
unified_posterior_learn_rate | 0.01 |
unified_likelihood_learn_rate | 0.0001 |
unified_prior_learn_rate | 0.001 |
unified_max_path_width | 10 |
Model Name | GraphDIVA | DIVA |
---|---|---|
/film/director/film | 0.565 | 0.565 |
/film/film/language | 0.728 | 0.728 |
/film/film/written_by | 0.756 | 0.709 |
/people/person/nationality | 0.862 | 0.834 |
/tv/tv/program_languages | 0.980 | 0.960 |
Average value | 0.778 | 0.759 |
Average value of the high-discrimination tasks | 0.866 | 0.834 |
Model Name | GraphDIVA | DIVA |
---|---|---|
athletehomestadium | 0.678 | 0.665 |
athleteplaysinleague | 0.909 | 0.871 |
organizationheadquarteredincity | 0.884 | 0.859 |
personborninlocation | 0.853 | 0.784 |
worksfor | 0.706 | 0.696 |
personleadsorganization | 0.756 | 0.746 |
Average value | 0.797 | 0.770 |
Average value of the high-discrimination tasks | 0.831 | 0.794 |
Model Name | GraphDIVA | DIVA |
---|---|---|
/film/director/film | 8 | 20 |
/film/film/language | 4 | 18 |
/film/film/written_by | 14 | 18 |
/people/person/nationality | 8 | 14 |
/tv/tv/program_languages | 8 | 10 |
Lead times | 5 | 0 |
Model Name | GraphDIVA | DIVA |
---|---|---|
athletehomestadium | 10 | 20 |
athleteplaysinleague | 14 | 16 |
organizationheadquarteredincity | 4 | 14 |
personborninlocation | 12 | 16 |
worksfor | 4 | 6 |
personleadsorganization | 18 | 12 |
Lead times | 4 | 2 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Tang, H.; Tang, W.; Li, R.; Wang, Y.; Wang, S.; Wang, L. Analysis of Knowledge Graph Path Reasoning Based on Variational Reasoning. Appl. Sci. 2022, 12, 6168. https://doi.org/10.3390/app12126168
Tang H, Tang W, Li R, Wang Y, Wang S, Wang L. Analysis of Knowledge Graph Path Reasoning Based on Variational Reasoning. Applied Sciences. 2022; 12(12):6168. https://doi.org/10.3390/app12126168
Chicago/Turabian StyleTang, Hongmei, Wenzhong Tang, Ruichen Li, Yanyang Wang, Shuai Wang, and Lihong Wang. 2022. "Analysis of Knowledge Graph Path Reasoning Based on Variational Reasoning" Applied Sciences 12, no. 12: 6168. https://doi.org/10.3390/app12126168