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

Neural network models often struggle with high-dimensional but smallsample-size tabular datasets. One reason is that current weight initialisationmethods assume independence between weights, which can be problematic whenthere are insufficient samples to estimate the model's parameters accurately.In such small data scenarios, leveraging additional structures can improve themodel's performance and training stability. To address this, we proposeGCondNet, a general approach to enhance neural networks by leveraging implicitstructures present in tabular data. We create a graph between samples for eachdata dimension, and utilise Graph Neural Networks (GNNs) for extracting thisimplicit structure, and for conditioning the parameters of the first layer ofan underlying predictor network. By creating many small graphs, GCondNetexploits the data's high-dimensionality, and thus improves the performance ofan underlying predictor network. We demonstrate the effectiveness of our methodon 9 real-world datasets, where GCondNet outperforms 15 standard andstate-of-the-art methods. The results show that GCondNet is a versatileframework for injecting graph-regularisation into various types of neuralnetworks, including MLPs and tabular Transformers.

GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data