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

Unsupervised node representations learnt using contrastive learning-basedmethods have shown good performance on downstream tasks. However, these methodsrely on augmentations that mimic low-pass filters, limiting their performanceon tasks requiring different eigen-spectrum parts. This paper presents a simplefilter-based augmentation method to capture different parts of theeigen-spectrum. We show significant improvements using these augmentations.Further, we show that sharing the same weights across these different filteraugmentations is possible, reducing the computational load. In addition,previous works have shown that good performance on downstream tasks requireshigh dimensional representations. Working with high dimensions increases thecomputations, especially when multiple augmentations are involved. We mitigatethis problem and recover good performance through lower dimensional embeddingsusing simple random Fourier feature projections. Our method, FiGURe achieves anaverage gain of up to 4.4%, compared to the state-of-the-art unsupervisedmodels, across all datasets in consideration, both homophilic and heterophilic.Our code can be found at: https://github.com/microsoft/figure.

FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations