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

Are Graph Neural Networks (GNNs) fair? In many real world graphs, theformation of edges is related to certain node attributes (e.g. gender,community, reputation). In this case, standard GNNs using these edges will bebiased by this information, as it is encoded in the structure of the adjacencymatrix itself. In this paper, we show that when metadata is correlated with theformation of node neighborhoods, unsupervised node embedding dimensions learnthis metadata. This bias implies an inability to control for importantcovariates in real-world applications, such as recommendation systems. To solvethese issues, we introduce the Metadata-Orthogonal Node Embedding Training(MONET) unit, a general model for debiasing embeddings of nodes in a graph.MONET achieves this by ensuring that the node embeddings are trained on ahyperplane orthogonal to that of the node metadata. This effectively organizesunstructured embedding dimensions into an interpretable topology-only,metadata-only division with no linear interactions. We illustrate theeffectiveness of MONET though our experiments on a variety of real worldgraphs, which shows that our method can learn and remove the effect ofarbitrary covariates in tasks such as preventing the leakage of political partyaffiliation in a blog network, and thwarting the gaming of embedding-basedrecommendation systems.

MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit