DLIN: Deep Ladder Imputation Network
| Autor: | Mehrdad Saif, Roozbeh Razavi-Far, Ehsan Hallaji |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Artificial Intelligence and Robotics
Computer science Generalization nonparametric models imputation computer.software_genre missing data Engineering Feature (machine learning) Imputation (statistics) Electrical and Electronic Engineering Flexibility (engineering) Computer Sciences Data Science Nonparametric statistics Deep learning denoising autoencoders (DAE) Electrical and Computer Engineering Missing data Computer Science Applications Human-Computer Interaction Research Design Control and Systems Engineering Benchmark (computing) Data mining computer ladder networks Algorithms Software Information Systems |
| Zdroj: | Electrical and Computer Engineering Publications |
| ISSN: | 2168-2275 2168-2267 |
| DOI: | 10.1109/tcyb.2021.3054878 |
| Popis: | Many efforts have been dedicated to addressing data loss in various domains. While task-specific solutions may eliminate the respective issue in certain applications, finding a generic method for missing data estimation is rather complex. In this regard, this article proposes a novel missing data imputation algorithm, which has supreme generalization ability for a vast variety of applications. Making use of both complete and incomplete parts of data, the proposed algorithm reduces the effect of missing ratio, which makes it suitable for situations with very high missing ratios. In addition, this feature enables model construction on incomplete training sets, which is rarely addressed in the literature. Moreover, the nonparametric nature of this new algorithm brings about supreme flexibility against all variations of missing values and data distribution. We incorporate the advantages of denoising autoencoders and ladder architecture into a novel formulation based on deep neural networks. To evaluate the proposed algorithm, a comparative study is performed using a number of reputable imputation techniques. In this process, real-world benchmark datasets from different domains are selected. On top of that, a real cyber-physical system is also evaluated to study the generalization ability of the proposed algorithm for distinct applications. To do so, we conduct studies based on three missing data mechanisms, namely: 1) missing completely at random; 2) missing at random; and 3) missing not at random. The attained results indicate the superiority of the proposed method in these experiments. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|