ABSTRACT
Knowledge acquisition is a process in which an artificial intelligence system acquires relevant knowledge from datasets. Knowledge acquisition extracts and forms knowledge from data of different structures. One type of data used to acquire knowledge is structured data, such as physics models, chemical structures, social network information, and traffic network information. Many structured data can be represented as graph structures with dependencies and attributes. In recent years, deep learning methods are applied to knowledge acquisition tasks. As a deep connection model, graph neural network (GNN) is suitable for processing data represented as graph structure since it can use nodes and edges to realize information interaction and obtain graph dependencies. In this review, we discuss GNN model and its variants. Experiments show that the variants of GNNs outperform traditional methods in many knowledge acquisition tasks.
- Kimbal, R. et al. 1998. The Data Warehouse Lifecycle Toolkit: Expert Methods for Designing, Developing, and Deploying Data Warehouses. John Wiley & Sons (Feb. 1998) DOI: http://dx.doi.org/Google Scholar
- Denney, M.J. et al. 2016. Validating the extract, transform, load process used to populate a large clinical research database. International Journal of Medical Informatics. 94, (Oct. 2016), 271 - 274. DOI: https://doi.org/10.1016/j.ijmedinf.2016.07.009.Google ScholarCross Ref
- Li, Y. et al. 2018. Incorporating knowledge into neural network for text representation. Expert Systems with Applications. 96, (Apr. 2018), 103--114. DOI: https://doi.org/10.1016/j.eswa.2017.11.037.Google ScholarDigital Library
- Jiafu, S. et al. 2018. Measuring knowledge diffusion efficiency in R&D networks. Knowledge Management Research & Practice. 16, 2 (Apr. 2018), 208 - 219. DOI: https://doi.org/10.1080/14778238.2018.1435186.Google ScholarCross Ref
- LeCun, Y. et al. 2015. Deep learning. Nature. 521, 7553 (May 2015), 436 - 444. DOI: https://doi.org/10.1038/nature 14539.Google ScholarCross Ref
- Scarselli, F. et al. 2009. The Graph Neural Network Model. IEEE Transactions on Neural Networks. 20, 1 (Jan. 2009), 61 - 80. DOI: https://doi.org/10.1109/TNN.2008.2005605.Google ScholarDigital Library
- Henaff, M. et al. 2015. Deep Convolutional Networks on Graph-Structured Data. arXiv: 1506.05163 [cs]. (Jun. 2015).Google Scholar
- Bruna, J. et al. 2014. Spectral Networks and Locally Connected Networks on Graphs. arXiv: 1312.6203 [cs]. (May 2014).Google Scholar
- Defferrard, M. et al. 2017. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. arXiv: 1606.09375 [cs, stat]. (Feb. 2017).Google Scholar
- Kipf, T.N. and Welling, M. 2017. Semi-Supervised Classification with Graph Convolutional Networks. arXiv: 1609.02907 [cs, stat]. (Feb. 2017).Google Scholar
- Thekumparampil, K.K. et al. 2018. Attention-based Graph Neural Network for Semi-supervised Learning. arXiv: 1803.03735 [cs, stat]. (Mar. 2018).Google Scholar
- Chaudhari, S. et al. 2019. An Attentive Survey of Attention Models. arXiv: 1904.02874 [cs, stat]. (Apr. 2019).Google Scholar
- Veličković, P. et al. 2018. Graph Attention Networks. arXiv: 1710.10903 [cs, stat]. (Feb. 2018).Google Scholar
- Atwood, J. and Towsley, D. 2016. Diffusion-Convolutional Neural Networks. arXiv:1511.02136 [cs]. (Jul. 2016).Google Scholar
- Zhang, Z. et al. 2019. Deep Learning on Graphs: A Survey. arXiv: 1812.04202 [cs, stat]. (Nov. 2019).Google Scholar
- Zhou, J. et al. 2019. Graph Neural Networks: A Review of Methods and Applications. arXiv: 1812.08434 [cs, stat].Google Scholar
- Wu, Z. et al. 2019. A Comprehensive Survey on Graph Neural Networks. arXiv:1901.00596 [cs, stat]. (Aug. 2019).Google Scholar
- Qiu, J. et al. 2018. DeepInf: Social Influence Prediction with Deep Learning. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD ' 18 (London, United Kingdom, 2018), 2110 - 2119.Google ScholarDigital Library
- Guo, S. et al. 2019. Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence. 33, (Jul. 2019), 922 - 929. DOI: https://doi.org/10.1609/aaai.v33i01.3301922Google ScholarDigital Library
- Hou, J. et al. 2019. Relational Reasoning using Prior Knowledge for Visual Captioning. arXiv:1906.01290 [cs]. (Jun. 2019).Google Scholar
Index Terms
- Theory and Applications of Graph Neural Networks in Knowledge Acquisition
Recommendations
Analysis on Interactive Structure of Knowledge Acquisition
ISISE '08: Proceedings of the 2008 International Symposium on Information Science and Engieering - Volume 02Knowledge Acquisition has been the focus in knowledge engineering for a long time. In this paper, knowledge acquisition technique based on structural analysis is formed by applying structural modeling, which is on basis of knowledge structural model. ...
The Impact of Knowledge Acquisition and Knowledge Integration of IT Outsourcing Supplier on Outsourcing Success -- Knowledge Sticky's Moderating Effect
ICSS '15: Proceedings of the 2015 International Conference on Service ScienceIn this study we analyze the emerging patterns of knowledge management of IT outsourcing supplier, which divided it into knowledge acquisition and knowledge integration, Since outsourcing success is related to a large amount of knowledge, it is of great ...
Study on Knowledge Acquisition Techniques
IITA '08: Proceedings of the 2008 Second International Symposium on Intelligent Information Technology Application - Volume 01The knowledge acquisition is a bottleneck of the artificial intelligence. How to extract knowledge effectively from the text is what knowledge engineering is concerned. Knowledge acquisition (KA) techniques give constrains to study and application of ...
Comments