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

In recent years, Graph Neural Network (GNN) has bloomly progressed for itspower in processing graph-based data. Most GNNs follow a message passingscheme, and their expressive power is mathematically limited by thediscriminative ability of the Weisfeiler-Lehman (WL) test. Following Tinhofer'sresearch on compact graphs, we propose a variation of the message passingscheme, called the Weisfeiler-Lehman-Tinhofer GNN (WLT-GNN), that theoreticallybreaks through the limitation of the WL test. In addition, we conductcomparative experiments and ablation studies on several well-known datasets.The results show that the proposed methods have comparable performances andbetter expressive power on these datasets.

Improving the Expressive Power of Graph Neural Network with Tinhofer Algorithm