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

Graph neural networks (GNNs), a type of neural network that can learn fromgraph-structured data and learn the representation of nodes through aggregatingneighborhood information, have shown superior performance in various downstreamtasks. However, it is known that the performance of GNNs degrades gradually asthe number of layers increases. In this paper, we evaluate the expressive powerof GNNs from the perspective of subgraph aggregation. We reveal the potentialcause of performance degradation for traditional deep GNNs, i.e., aggregatedsubgraph overlap, and we theoretically illustrate the fact that previousresidual-based GNNs exploit the aggregation results of 1 to $k$ hop subgraphsto improve the effectiveness. Further, we find that the utilization ofdifferent subgraphs by previous models is often inflexible. Based on this, wepropose a sampling-based node-level residual module (SNR) that can achieve amore flexible utilization of different hops of subgraph aggregation byintroducing node-level parameters sampled from a learnable distribution.Extensive experiments show that the performance of GNNs with our proposed SNRmodule outperform a comprehensive set of baselines.

Deep Graph Neural Networks via Flexible Subgraph Aggregation