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

Variational Autoencoders and their many variants have displayed impressiveability to perform dimensionality reduction, often achieving state-of-the-artperformance. Many current methods however, struggle to learn goodrepresentations in High Dimensional, Low Sample Size (HDLSS) tasks, which is aninherently challenging setting. We address this challenge by using an ensembleof lightweight VAEs to learn posteriors over subsets of the feature-space,which get aggregated into a joint posterior in a novel divide-and-conquerapproach. Specifically, we present an alternative factorisation of the jointposterior that induces a form of implicit data augmentation that yields greatersample efficiency. Through a series of experiments on eight real-worlddatasets, we show that our method learns better latent representations in HDLSSsettings, which leads to higher accuracy in a downstream classification task.Furthermore, we verify that our approach has a positive effect ondisentanglement and achieves a lower estimated Total Correlation on learntrepresentations. Finally, we show that our approach is robust to partialfeatures at inference, exhibiting little performance degradation even with mostfeatures missing.

Enhancing Representation Learning on High-Dimensional, Small-Size Tabular Data: A Divide and Conquer Method with Ensembled VAEs