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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Data is commonly stored in tabular format. Several fields of research areprone to small imbalanced tabular data. Supervised Machine Learning on suchdata is often difficult due to class imbalance. Synthetic data generation,i.e., oversampling, is a common remedy used to improve classifier performance.State-of-the-art linear interpolation approaches, such as LoRAS and ProWRAS canbe used to generate synthetic samples from the convex space of the minorityclass to improve classifier performance in such cases. Deep generative networksare common deep learning approaches for synthetic sample generation, widelyused for synthetic image generation. However, their scope on synthetic tabulardata generation in the context of imbalanced classification is not adequatelyexplored. In this article, we show that existing deep generative models performpoorly compared to linear interpolation based approaches for imbalancedclassification problems on smaller tabular datasets. To overcome this, wepropose a deep generative model, ConvGeN that combines the idea of convex spacelearning with deep generative models. ConvGeN learns the coefficients for theconvex combinations of the minority class samples, such that the synthetic datais distinct enough from the majority class. Our benchmarking experimentsdemonstrate that our proposed model ConvGeN improves imbalanced classificationon such small datasets, as compared to existing deep generative models, whilebeing at-par with the existing linear interpolation approaches. Moreover, wediscuss how our model can be used for synthetic tabular data generation ingeneral, even outside the scope of data imbalance and thus, improves theoverall applicability of convex space learning.

ConvGeN: Convex space learning improves deep-generative oversampling for tabular imbalanced classification on smaller datasets