Anqi Tian
ABSTRACT
Knowledge graphs display various entities and their relationships in the real world based on knowledge representation and can analyze and predict the intrinsic relationship between knowledge embeddings through data mining and information processing, which are widely used in search engines, web analytics and smart recommendation areas. As existing knowledge graph information is continuously created and grown, it is a curial task to determine whether the information in knowledge graph is correct and to complete the missing information. In response to this challenge, the researchers proposed a number of graph convolutional network (GCN)-based models to characterize knowledge graphs. The state-of-the-art model is R-GCN, which can effectively extract features. This paper deeply studies the algorithm ideas and results of the R-GCN model, explores whether the model can be further optimized in entity classification and link prediction, and finally, improves the original model and proposes a relational aggregation graph convolutional network. Specifically, this paper finds that a subset of the set of entities may be directly connected to a central entity. All the entities in this subset possess partially identical attributes. At the same time, the relationships between these entities and the central entity may be similar. These similar attributes and relationships can be abstractly aggregated into virtual entities and virtual relationships, respectively, to better extract the topological relationship features. This paper uses the FB15k dataset to evaluate the performance of the proposed model on knowledge graph completion tasks. The experimental results show that the proposed RA-GCN model achieves a certain level improvement compared with the original model and that it can extract knowledge graph topological relationship characteristics more effectively.
- Bhagat, S., Cormode, G., and Muthukrishnan, S. 2011. Node classification in social networks. Comput. Sc. 16, 3 (Mar. 2011), 115--148. DOI= https://doi.org/10.1007/978-1-4419-8462-3_5.Google Scholar
- Bronstein, M. M., Bruna, J., LeCun, Y., Szlam, A., and Vandergheynst, P. 2017. Geometric deep learning: going beyond Euclidean data. IEEE Signal Proc. Mag. 34, 4 (Jul. 2017), 18--42. DOI=http://doi.acm.org/10.1109/MSP.2017.2693418.Google ScholarCross Ref
- Duvenaud, D., Maclaurin, D., Aguilera-Iparraguirre, J., Gmez-Bombarelli, R., Hirzel, T., Aspuru-Guzik, A., and Adams, R. P. 2015. Convolutional networks on graphs for learning molecular fingerprints. In Proceedings of the 28th International Conference on Neural Information Processing Systems (Montreal, Canada, December 07-12, 2015). MIT Press, Cambridge, MA, USA, 2224--2232.Google Scholar
- Hammond, D. K., Vandergheynst, P., and Gribonval, R. 2011. Wavelets on graphs via spectral graph theory. Appl. Comput. Harmon. A. 30, 2 (Mar. 2011), 129--150. DOI=https://doi.org/10.1016/j.acha.2010.04.005.Google ScholarCross Ref
- Kingma, D., and Ba, J. 2014. Adam: a method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations (ICLR) (San Diego, USA, May 07-09, 2015). arXiv preprint arXiv: 1412.6980, Ithaca, NY.Google Scholar
- Kipf, T., and Welling, M. 2016. Semi-supervised classification with graph convolutional networks. In ICLR 2016 (Caribe Hilton, San Juan, Puerto Rico, September 09, 2016). arXiv preprint arXiv: 1609.02907.Google Scholar
- Lee, J. A., and Verleysen, M. 2007. Nonlinear Dimensionality Reduction. Springer Science and Business Media, New York, NY.Google Scholar
- Liao, W., Xia, J., Du, P., and Philips, W. 2015. Semi-supervised graph fusion of hyperspectral and lidar data for classification. In 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (Milan, Italy, July 26-31, 2015). IEEE, Milan, Italy, 53--56. DOI=http://doi.acm.org/10.1109/IGARSS.2015.7325695.Google Scholar
- Nickel, M., Murphy, K., Tresp, V., and Gabrilovich, E. 2016. A review of relational machine learning for knowledge graphs. Proc. IEEE. 104, 1 (Dec. 2015), 11--33. DOI=https://doi.org/10.1109/JPROC.2015.2483592.Google ScholarCross Ref
- Nickel, M., Tresp, V., and 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 (Washington, DC, USA, June 28 -- July 02). Omnipress, New York, NY, 809--816.Google Scholar
- Schlichtkrull, M., Kipf, T. N., Bloem, P., Van den Berg, R., Titov, I., and Welling, M. 2018. Modeling relational data with graph convolutional networks. In European Semantic Web Conference (Heraklion, Greece, June 03 -- 07, 2018). Springer, Cham, 593--607. DOI= https://doi.org/10.1007/978-3-319-93417-4_38.Google ScholarDigital Library
- Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., and Bouchard, G. 2016. Complex embeddings for simple link prediction. In Proceedings of the 33rd International Conference on Machine Learning (New York, NY, USA, June 19 -- 24, 2016). JMLR.org, 2071--2080.Google Scholar
- Yang, B., Yih, W.-T., He, X., Gao, J., and Deng, L. 2014. Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint arXiv: 1412.6575. (Dec. 2014).Google Scholar
Index Terms
- RA-GCN: Relational Aggregation Graph Convolutional Network for Knowledge Graph Completion
Recommendations
Knowledge Embedding Based Graph Convolutional Network
WWW '21: Proceedings of the Web Conference 2021Recently, a considerable literature has grown up around the theme of Graph Convolutional Network (GCN). How to effectively leverage the rich structural information in complex graphs, such as knowledge graphs with heterogeneous types of entities and ...
Knowledge Graph Augmentation with Entity Identification for Improving Knowledge Graph Completion Performance
PRICAI 2023: Trends in Artificial IntelligenceAbstractA knowledge graph often lacks some existent triples. Knowledge graph completion is a technique for complementing such triples and its performance can be improved by augmenting triples from other external databases. However, entity names often ...
A Comprehensive Survey on Automatic Knowledge Graph Construction
Automatic knowledge graph construction aims at manufacturing structured human knowledge. To this end, much effort has historically been spent extracting informative fact patterns from different data sources. However, more recently, research interest has ...
Comments