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

Graph Neural Networks have emerged as a useful tool to learn on the data byapplying additional constraints based on the graph structure. These graphs areoften created with assumed intrinsic relations between the entities. In recentyears, there have been tremendous improvements in the architecture design,pushing the performance up in various prediction tasks. In general, theseneural architectures combine layer depth and node feature aggregation steps.This makes it challenging to analyze the importance of features at various hopsand the expressiveness of the neural network layers. As different graphdatasets show varying levels of homophily and heterophily in features and classlabel distribution, it becomes essential to understand which features areimportant for the prediction tasks without any prior information. In this work,we decouple the node feature aggregation step and depth of graph neural networkand introduce several key design strategies for graph neural networks. Morespecifically, we propose to use softmax as a regularizer and "Soft-Selector" offeatures aggregated from neighbors at different hop distances; and"Hop-Normalization" over GNN layers. Combining these techniques, we present asimple and shallow model, Feature Selection Graph Neural Network (FSGNN), andshow empirically that the proposed model outperforms other state of the art GNNmodels and achieves up to 64% improvements in accuracy on node classificationtasks. Moreover, analyzing the learned soft-selection parameters of the modelprovides a simple way to study the importance of features in the predictiontasks. Finally, we demonstrate with experiments that the model is scalable forlarge graphs with millions of nodes and billions of edges.

Improving Graph Neural Networks with Simple Architecture Design