Missing Data Imputation for Supervised Learning
By Jason Poulos, Rafael Valle. 2016
74 citations recorded by the source corpus.
ABSTRACT Missing data imputation can help improve the performance of prediction models in situations where missing data hide useful information. This paper compares methods for imputing missing categorical data for supervised classification tasks. We experiment on two machine learning benchmark datasets with missing categorical data, comparing classifiers trained on non-imputed (i.e., one-hot encoded) or imputed data with different levels of additional missing-data perturbation. We show imputation methods can increase predictive accuracy in the presence of missing-data perturbation, which can actually improve prediction accuracy by regularizing the classifier. We achieve results comparable to the state-of-the-art on the Adult dataset with missing-data perturbation and -nearest-neighbors (-NN) imputation.
Subfields: Artificial Intelligence, Statistics and Probability, Evaluation & Benchmarks
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Nicolas Papernot
- Nicholas Carlini
- Kunal Talwar
- Florian Tramèr
- Ian J. Goodfellow
- Ú. Erlingsson
- Dawn Song
- Percy Liang
In Statistics and Probability
- Anil S. Jadhav
- Ian J. Goodfellow
- Ú. Erlingsson
- Krishnan Ramanathan
- Nicolas Papernot
- Kunal Talwar
- Dhanya Pramod
In Evaluation & Benchmarks
- Anil S. Jadhav
- Ian J. Goodfellow
- Ú. Erlingsson
- Martín Abadi
- Krishnan Ramanathan
- Nicolas Papernot
- Kunal Talwar
- Dhanya Pramod
Citations in the corpus
- Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data (2016, methodology): “Our non-private model on the dataset achieves 85% accuracy, which is comparable to the state-of-the-art accuracy of 86% on this dataset (Poulos & Valle, 2016).”
- Comparison of Performance of Data Imputation Methods for Numeric Dataset (2019, methodology): “Poulos and Valle (2016) compared methods for missing categorical data for supervised learning task using two datasets.”