Imputation Using a Correlation-Enhanced Auto-Associative Neural Network with Dynamic Processing of Missing Values
The missing value is a common phenomenon in real-world datasets, which makes the analysis of incomplete data become an active research area. In this paper, a correlation-enhanced auto-associative neural network (CE-AANN) is proposed for imputations of missing values. We design correlation-enhanced hidden neurons and combine them with traditional hidden neurons organically, thereby constructing CE-AANN. Compared with the traditional auto-associative neural network (AANN), the improved architecture can mine cross-correlations among attributes more effectively. The introduction of correlation-enhanced hidden neurons keeps the network from learning a meaningless identity mapping. Moreover, a training scheme named MVPT is used for network training. Missing values are regarded as variables of the loss function and adjusted dynamically based on optimization algorithms. The dynamic processing mechanism takes account of the incompleteness of data during training, which makes the imputation accuracy increase as the training goes further. Experiments validate the effectiveness of the proposed method.
KeywordsIncomplete data Missing value imputation Auto-associative neural network Dynamic processing mechanism
This work was supported by National Key R&D Program of China (2018YFB1700200).
- 1.Garcíalaencina, P.J., Sanchogómez, J., Figueirasvidal, A.R.: Pattern classification with missing data: a review. Neural Comput. Appl. 19(2), 263–282 (2010)Google Scholar
- 2.Masoud, S.A., Negin, D.: Missing value imputation using a novel grey based fuzzy c-means, mutual information based feature selection, and regression model. Expert Syst. Appl. 115, 68–94 (2019)Google Scholar
- 3.Azim, S., Aggarwal, S.: Using fuzzy c means and multi layer perceptron for data imputation: simple v/s complex dataset. In: 2016 3rd International Conference on Recent Advances in Information Technology (RAIT), pp. 197–202. IEEE (2016)Google Scholar
- 4.Abdella, M., Marwala, T.: The use of genetic algorithms and neural networks to approximate missing data in database. In: 2015 3rd IEEE International Conference on Computational Cybernetics (ICCC), pp. 207–212. IEEE (2005)Google Scholar
- 5.Nelwamondo, F.V., Golding, D.: A dynamic programming approach to missing data estimation using neural networks. Inf. Sci. 237, 49–58 (2013)Google Scholar
- 6.Aydilek, I.B., Arslan, A.: A novel hybrid approach to estimating missing values in databases using k-nearest neighbors and neural networks. Int. J. Innovative Comput. Inf. Control 7(8), 4705–4717 (2012)Google Scholar
- 7.Ravi, V., Krishna, M.: A new online data imputation method based on general regression auto associative neural network. Neurocomputing 138, 106–113 (2014)Google Scholar
- 8.Gautam, C., Ravi, V.: Counter propagation auto-associative neural network based data imputation. Inf. Sci. 325, 288–299 (2015)Google Scholar
- 9.Mistry, F.J., Nelwamondo, F.V., Marwala, T.: Missing data estimation using principle component analysis and autoassociative neural networks. J. Syst. Cybern. Inf. 7(3), 72–79 (2009)Google Scholar
- 10.Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT press, Cambridge (2016)Google Scholar