Learning from data with structured missingness

Mitra, Robin and McGough, Sarah F. and Chakraborti, Tapabrata and Holmes, Chris and Copping, Ryan and Hagenbuch, Niels and Biedermann, Stefanie and Noonan, Jack and Lehmann, Brieuc and Shenvi, Aditi and Doan, Xuan Vinh and Leslie, David and Bianconi, Ginestra and Sanchez-Garcia, Ruben and Davies, Alisha and Mackintosh, Maxine and Andrinopoulou, Eleni-Rosalina and Basiri, Anahid and Harbron, Chris and MacArthur, Ben D. (2023) Learning from data with structured missingness. Nature Machine Intelligence, 5 (1). pp. 13-23. ISSN 2522-5839

Full text not available from this repository.


Missing data are an unavoidable complication in many machine learning tasks. When data are ‘missing at random’ there exist a range of tools and techniques to deal with the issue. However, as machine learning studies become more ambitious, and seek to learn from ever-larger volumes of heterogeneous data, an increasingly encountered problem arises in which missing values exhibit an association or structure, either explicitly or implicitly. Such ‘structured missingness’ raises a range of challenges that have not yet been systematically addressed, and presents a fundamental hindrance to machine learning at scale. Here we outline the current literature and propose a set of grand challenges in learning from data with structured missingness.

Item Type:
Journal Article
Journal or Publication Title:
Nature Machine Intelligence
ID Code:
Deposited By:
Deposited On:
09 Mar 2023 10:05
Last Modified:
09 Mar 2023 10:05