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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Unsupervised Representation Learning on graphs is gaining traction due to theincreasing abundance of unlabelled network data and the compactness, richness,and usefulness of the representations generated. In this context, the need toconsider fairness and bias constraints while generating the representations hasbeen well-motivated and studied to some extent in prior works. One majorlimitation of most of the prior works in this setting is that they do not aimto address the bias generated due to connectivity patterns in the graphs, suchas varied node centrality, which leads to a disproportionate performance acrossnodes. In our work, we aim to address this issue of mitigating bias due toinherent graph structure in an unsupervised setting. To this end, we proposeCAFIN, a centrality-aware fairness-inducing framework that leverages thestructural information of graphs to tune the representations generated byexisting frameworks. We deploy it on GraphSAGE (a popular framework in thisdomain) and showcase its efficacy on two downstream tasks - Node Classificationand Link Prediction. Empirically, CAFIN consistently reduces the performancedisparity across popular datasets (varying from 18 to 80% reduction inperformance disparity) from various domains while incurring only a minimal costof fairness.

CAFIN: Centrality Aware Fairness inducing IN-processing for Unsupervised Representation Learning on Graphs