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

Despite recent advances in achieving fair representations and predictionsthrough regularization, adversarial debiasing, and contrastive learning ingraph neural networks (GNNs), the working mechanism (i.e., message passing)behind GNNs inducing unfairness issue remains unknown. In this work, wetheoretically and experimentally demonstrate that representative aggregation inmessage-passing schemes accumulates bias in node representation due to topologybias induced by graph topology. Thus, a \textsf{F}air \textsf{M}essage\textsf{P}assing (FMP) scheme is proposed to aggregate useful information fromneighbors but minimize the effect of topology bias in a unified frameworkconsidering graph smoothness and fairness objectives. The proposed FMP iseffective, transparent, and compatible with back-propagation training. Anacceleration approach on gradient calculation is also adopted to improvealgorithm efficiency. Experiments on node classification tasks demonstrate thatthe proposed FMP outperforms the state-of-the-art baselines in effectively andefficiently mitigating bias on three real-world datasets.

FMP: Toward Fair Graph Message Passing against Topology Bias