English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The problem of missing data has been persistent for a long time and poses amajor obstacle in machine learning and statistical data analysis. Past works inthis field have tried using various data imputation techniques to fill in themissing data, or training neural networks (NNs) with the missing data. In thiswork, we propose a simple yet effective approach that clusters similar inputfeatures together using hierarchical clustering and then trains proportionatelysplit neural networks with a joint loss. We evaluate this approach on a seriesof benchmark datasets and show promising improvements even with simpleimputation techniques. We attribute this to learning through clusters ofsimilar features in our model architecture. The source code is available athttps://github.com/usarawgi911/Robustness-to-Missing-Features

Robustness to Missing Features using Hierarchical Clustering with Split Neural Networks