Research Topic

Missing Data Imputation in Static and Temporal Settings

About this Research Topic

Missing data is a pervasive problem and many real-world datasets (especially in medicine and sociology) include small or large portions of missing data. Data may be missing for many reasons: some variables may not have been measured (perhaps because it was deemed unnecessary/unimportant, or with the goal of ...

Missing data is a pervasive problem and many real-world datasets (especially in medicine and sociology) include small or large portions of missing data. Data may be missing for many reasons: some variables may not have been measured (perhaps because it was deemed unnecessary/unimportant, or with the goal of reducing destructive sampling) or accidentally not recorded. However, most state-of-the-art machine learning models and data analysis tools are only applicable when the input data is complete. Therefore, one of the critical parts of the machine learning pipeline is how to deal with the missing values. Proper handling of the missing data (e.g., imputation) is vital in machine learning and big data analyses.

A proposed solution to the missing data problem is the rise of imputation algorithms. An imputation algorithm estimates missing values based on data that was observed/measured. Accurate imputation algorithms are critical for constructing accurate predictive models. For instance, in medicine, accurately imputed data (via state-of-the-art imputation algorithms) would significantly improve the predictive performance on diagnosis and prognosis.
This Research Topic aims to advance the literature on imputation algorithms with the expectation that this will subsequently lead to higher accuracy in the missing measurement estimations. The development of this research area will have wider implications for accurate downstream predictions as well as other applications such as image concealment, data compression, and counterfactual estimation. Thus, proposing the novel imputation algorithms and evaluating them on various use-cases in big data analyses is the main goal of this research topic.

Subtopics of interest include, but are not limited to
- Missing data imputation on irregularly sampled time-series/spatio-temporal data
- Novel machine learning methods for image inpainting and video frame interpolation
- Missing data imputation on tabular data with mixed-type data (including both categorical and continuous variables)
- Robust predictive model construction on data with a large portion of missing values
- Novel machine learning methods for handling missing at random (MAR) and missing not at random (MNAR) settings
- Interpretable machine learning for data imputation


Keywords: Missing Data, Imputation, Incomplete Data, Interpolation, Irregular Sampling


Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.

Recent Articles

Loading..

About Frontiers Research Topics

With their unique mixes of varied contributions from Original Research to Review Articles, Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area! Find out more on how to host your own Frontiers Research Topic or contribute to one as an author.

Topic Editors

Loading..

Submission Deadlines

11 April 2021 Manuscript
11 May 2021 Manuscript Extension

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..

Topic Editors

Loading..

Submission Deadlines

11 April 2021 Manuscript
11 May 2021 Manuscript Extension

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..
Loading..

total views article views article downloads topic views

}
 
Top countries
Top referring sites
Loading..