An Overview of Knowledge Graph Reasoning: Key Technologies and Applications
Abstract
:1. Introduction
2. Brief Introduction to Knowledge Graphs
2.1. Knowledge Representation
2.2. Knowledge Extraction
- Named entity recognition: the detection of named entities from text and classification of them into predefined categories, such as person, organization, place, time, etc. In general, named entity recognition is the basis of other knowledge extraction tasks.
- Relationship extraction: the identification and extraction of entities and relationships between entities from the text. For example, from the sentence “[Steve Jobs] is one of the founders of [Apple]”, the entities “[Steve Jobs]” and “[Apple]” are identified as having a “is-founder-of” relationship.
- Event extraction: the identification of the information about the event in the text and presentation of it in a structured form. For example, information such as location, time, target, and victim can be identified from news reports of terrorist attacks.
2.2.1. Named Entity Recognition
2.2.2. Relationship Extraction
2.2.3. Event Extraction
2.3. Knowledge Fusion
3. Knowledge Graph Reasoning
3.1. Introduction
3.2. Methods of Knowledge Graph Reasoning
3.2.1. Embedding-Based Reasoning
3.2.2. Symbolic-Based Reasoning
3.2.3. Neural Network-Based Reasoning
3.2.4. Mixed Reasoning
4. Comparisons and Analysis
- Knowledge graph embedding is usually embedded in Euclidean space. In recent years, MuRP, ATTH, and other models have explored the case of embedding in hyperbolic space and achieved very good results. However, in general, there are few studies on embedding knowledge graphs into hyperbolic space. Some models show that hyperbolic space and other non-Euclidean Spaces can better express knowledge graphs. The representation and reasoning of knowledge graph in non-Euclidean space is worth further exploration.
- Graph neural network natural matching knowledge graphs such as r-GCN and R GHAT models introduced in this paper are still early attempts and are far from perfect. The design of more sophisticated graph network structures to realize knowledge graph reasoning is a hot and promising direction.
- Transformer networks excel because of their strong expression ability and efficient parallel training ability in the field of natural language processing, and can be quickly migrated to computer vision, image processing, and speech recognition, in which the results are equally outstanding. It is believed that the converter network can also perform well in knowledge graphs and knowledge graph reasoning.
- Transfer learning based on the pre-training of models is widely used in natural language processing, image processing, and computer vision, but is rarely used in knowledge graph reasoning. It is worth exploring pre-training models in knowledge graphs and knowledge graph reasoning.
- Modern knowledge graph reasoning techniques also have great opportunities in data sets and corresponding contests and evaluations, especially in Chinese knowledge graph data sets.
5. Applications
5.1. Wireless Communication Networks (WCN)
5.2. Question Answering (QA) Systems
5.3. Recommendation Systems
5.4. Personalized Search
6. Future Directions
7. Summary
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Ren, H.; Dai, H.; Dai, B.; Chen, X.; Zhou, D.; Leskovec, J.; Schuurmans, D. SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, 14–18 August 2022. [Google Scholar]
- Ji, S.; Pan, S.; Cambria, E.; Marttinen, P.; Yu, P.S. A Survey on Knowledge Graphs: Representation, Acquisition, and Applications. IEEE Trans. Neural Netw. Learn. Syst. 2022, 33, 494–514. [Google Scholar] [CrossRef] [PubMed]
- Wu, Y.; Ma, Y.; Wan, S. Multi-scale relation reasoning for multi-modal Visual Question Answering. Signal Process. Image Commun. 2021, 96, 116319. [Google Scholar] [CrossRef]
- Wu, Y.; Ji, X.; Ji, W.; Tian, Y.; Zhou, H. CASR: A context-aware residual network for single-image super-resolution. Neural Comput. Appl. 2020, 32, 14533–14548. [Google Scholar] [CrossRef]
- Li, G.; He, B.; Wang, Z.; Zhou, Y. A Data Agent Inspired by Interpersonal Interaction Behaviors for Wireless Sensor Networks. IEEE Internet Things J. 2022, 9, 8397–8411. [Google Scholar] [CrossRef]
- ** Matrix. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics (ACL), Bei**g, China, 26–31 July 2015; pp. 687–696. [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, Québec City, QC, Canada, 27–31 July 2014. [Google Scholar]
- Cohen, W.W. TensorLog: A Differentiable Deductive Database. ar**v 2016, ar**v:1605.06523. [Google Scholar]
- Wang, W.Y.; Mazaitis, K.; Cohen, W.W. Programming with personalized pagerank: A locally groundable first-order probabilistic logic. In Proceedings of the 22nd ACM International Conference on Information and Knowledge Management, CIKM’13, San Francisco, CA, USA, 27 October–1 November 2013; pp. 2129–2138. [Google Scholar]
- Wang, W.Y.; Mazaitis, K.; Lao, N.; Cohen, W.W. Efficient reasoning and learning in a large knowledge base—Reasoning with extracted information using a locally groundable first-order probabilistic logic. Mach. Learn. 2015, 100, 101–126. [Google Scholar] [CrossRef] [Green Version]
- Paulheim, H.; Bizer, C. Improving the Quality of Linked Data Using Statistical Distributions. Int. J. Semant. Web Inf. Syst. 2014, 10, 63–86. [Google Scholar] [CrossRef]
- Jang, S.; Megawati; Choi, J.; Yi, M.Y. Semi-Automatic Quality Assessment of Linked Data without Requiring Ontology. In Proceedings of the 14th International Semantic Web Conference (ISWC), Bethlehem, PA, USA, 11 October 2015; pp. 45–55. [Google Scholar]
- Shen, Y.; Huang, P.-S.; Chang, M.; Gao, J. Implicit ReasoNet: Modeling Large-Scale Structured Relationships with Shared Memory. ar**v 2016, ar**v:1611.04642v1. [Google Scholar]
- Shi, B.; Weninger, T. Open-World Knowledge Graph Completion. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, LA, USA, 2–7 February 2018; pp. 1957–1964. [Google Scholar]
- Wang, X.; He, X.; Cao, Y.; Liu, M.; Chua, T.-S. KGAT: Knowledge Graph Attention Network for Recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2019, Anchorage, AK, USA, 4–8 August 2019. [Google Scholar]
- Guo, S.; Wang, Q.; Wang, L.; Wang, B.; Guo, L. Jointly embedding knowledge graphs and logical rules. In Proceedings of the Empirical Methods in Natural Language Processing, Austin, TX, USA, 1–4 November 2016; pp. 1488–1498. [Google Scholar]
- Tay, Y.; Luu, A.T.; Hui, S.C. Non-Parametric estimation of multiple embeddings for link prediction on dynamic knowledge graphs. In Proceedings of the 31st AAAI Conference on Artificial Intelligence, San Francisco, CA, USA, 4–9 February 2017; pp. 1243–1249. [Google Scholar]
Method | Advantages | Disadvantages |
---|---|---|
TransE series (embedding-based reasoning) | Simple, fast speed. | Only suitable for one-to-one relationships. |
AMIE (symbolic-based reasoning) | Interpretable; automatic discovery of rules. | With large search space and low coverage of generated rules, the prediction effect of the final model is also poor. |
NTN (neural network-based reasoning) | More resilient against the sparsity problem. | High complexity; requires a large number of triples to be fully learned. |
R-GCN (neural network-based reasoning) | The graph product network is introduced into knowledge reasoning domain for the first time. | Unstable; as the number of relationships increases, the number of parameters explodes, introducing too many relationship matrices. |
IRN (neural network-based reasoning) | Stores knowledge through shared memory components. Can simulate the human brain to learn multi-step reasoning process. | Has difficulty with unstructured data and self-heating language query. |
ConMask (mixed reasoning) | Can add unknown new entities from outside the knowledge graph and link them to internal entity nodes. | When no text pair that can accurately describe entities or relations appears, the model cannot obtain enough reasoning basis, resulting in poor reasoning effect. |
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
Chen, Y.; Li, H.; Li, H.; Liu, W.; Wu, Y.; Huang, Q.; Wan, S. An Overview of Knowledge Graph Reasoning: Key Technologies and Applications. J. Sens. Actuator Netw. 2022, 11, 78. https://doi.org/10.3390/jsan11040078
Chen Y, Li H, Li H, Liu W, Wu Y, Huang Q, Wan S. An Overview of Knowledge Graph Reasoning: Key Technologies and Applications. Journal of Sensor and Actuator Networks. 2022; 11(4):78. https://doi.org/10.3390/jsan11040078
Chicago/Turabian StyleChen, Yonghong, Hao Li, Han Li, Wenhao Liu, Yirui Wu, Qian Huang, and Shaohua Wan. 2022. "An Overview of Knowledge Graph Reasoning: Key Technologies and Applications" Journal of Sensor and Actuator Networks 11, no. 4: 78. https://doi.org/10.3390/jsan11040078