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

Recently, graph neural networks (GNNs) have shown prominent performance ingraph representation learning by leveraging knowledge from both graph structureand node features. However, most of them have two major limitations. First,GNNs can learn higher-order structural information by stacking more layers butcan not deal with large depth due to the over-smoothing issue. Second, it isnot easy to apply these methods on large graphs due to the expensivecomputation cost and high memory usage. In this paper, we present node-adaptivefeature smoothing (NAFS), a simple non-parametric method that constructs noderepresentations without parameter learning. NAFS first extracts the features ofeach node with its neighbors of different hops by feature smoothing, and thenadaptively combines the smoothed features. Besides, the constructed noderepresentation can further be enhanced by the ensemble of smoothed featuresextracted via different smoothing strategies. We conduct experiments on fourbenchmark datasets on two different application scenarios: node clustering andlink prediction. Remarkably, NAFS with feature ensemble outperforms thestate-of-the-art GNNs on these tasks and mitigates the aforementioned twolimitations of most learning-based GNN counterparts.

NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning