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

Traditional classification tasks learn to assign samples to given classesbased solely on sample features. This paradigm is evolving to include othersources of information, such as known relations between samples. Here we showthat, even if additional relational information is not available in the dataset, one can improve classification by constructing geometric graphs from thefeatures themselves, and using them within a Graph Convolutional Network. Theimprovement in classification accuracy is maximized by graphs that capturesample similarity with relatively low edge density. We show that suchfeature-derived graphs increase the alignment of the data to the ground truthwhile improving class separation. We also demonstrate that the graphs can bemade more efficient using spectral sparsification, which reduces the number ofedges while still improving classification performance. We illustrate ourfindings using synthetic and real-world data sets from various scientificdomains.

Geometric graphs from data to aid classification tasks with graph convolutional networks