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

Class imbalance is the phenomenon that some classes have much fewer instancesthan others, which is ubiquitous in real-world graph-structured scenarios.Recent studies find that off-the-shelf Graph Neural Networks (GNNs) wouldunder-represent minor class samples. We investigate this phenomenon anddiscover that the subspaces of minor classes being squeezed by those of themajor ones in the latent space is the main cause of this failure. We arenaturally inspired to enlarge the decision boundaries of minor classes andpropose a general framework GraphSHA by Synthesizing HArder minor samples.Furthermore, to avoid the enlarged minor boundary violating the subspaces ofneighbor classes, we also propose a module called SemiMixup to transmitenlarged boundary information to the interior of the minor classes whileblocking information propagation from minor classes to neighbor classes.Empirically, GraphSHA shows its effectiveness in enlarging the decisionboundaries of minor classes, as it outperforms various baseline methods inclass-imbalanced node classification with different GNN backbone encoders overseven public benchmark datasets. Code is avilable athttps://github.com/wenzhilics/GraphSHA.

GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification