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

Recent years have witnessed fast developments of graph neural networks (GNNs)that have benefited myriads of graph analytic tasks and applications. Ingeneral, most GNNs depend on the homophily assumption that nodes belonging tothe same class are more likely to be connected. However, as a ubiquitous graphproperty in numerous real-world scenarios, heterophily, i.e., nodes withdifferent labels tend to be linked, significantly limits the performance oftailor-made homophilic GNNs. Hence, \textit{GNNs for heterophilic graphs} aregaining increasing attention in this community. To the best of our knowledge,in this paper, we provide a comprehensive review of GNNs for heterophilicgraphs for the first time. Specifically, we propose a systematic taxonomy thatessentially governs existing heterophilic GNN models, along with a generalsummary and detailed analysis. Furthermore, we summarize the mainstreamheterophilic graph benchmarks to facilitate robust and fair evaluations. In theend, we point out the potential directions to advance and stimulate futureresearch and applications on heterophilic graphs.

Graph Neural Networks for Graphs with Heterophily: A Survey