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

Heterogeneous graph neural networks (HGNNs) have been blossoming in recentyears, but the unique data processing and evaluation setups used by each workobstruct a full understanding of their advancements. In this work, we present asystematical reproduction of 12 recent HGNNs by using their official codes,datasets, settings, and hyperparameters, revealing surprising findings aboutthe progress of HGNNs. We find that the simple homogeneous GNNs, e.g., GCN andGAT, are largely underestimated due to improper settings. GAT with properinputs can generally match or outperform all existing HGNNs across variousscenarios. To facilitate robust and reproducible HGNN research, we constructthe Heterogeneous Graph Benchmark (HGB), consisting of 11 diverse datasets withthree tasks. HGB standardizes the process of heterogeneous graph data splits,feature processing, and performance evaluation. Finally, we introduce a simplebut very strong baseline Simple-HGN--which significantly outperforms allprevious models on HGB--to accelerate the advancement of HGNNs in the future.

Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks