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) learn the representation of nodes in a graph byaggregating the neighborhood information in various ways. As these networksgrow in depth, their receptive field grows exponentially due to the increase inneighborhood sizes, resulting in high memory costs. Graph sampling solvesmemory issues in GNNs by sampling a small ratio of the nodes in the graph. Thisway, GNNs can scale to much larger graphs. Most sampling methods focus on fixedsampling heuristics, which may not generalize to different structures or tasks.We introduce GRAPES, an adaptive graph sampling method that learns to identifysets of influential nodes for training a GNN classifier. GRAPES uses a GFlowNetto learn node sampling probabilities given the classification objectives. Weevaluate GRAPES across several small- and large-scale graph benchmarks anddemonstrate its effectiveness in accuracy and scalability. In contrast toexisting sampling methods, GRAPES maintains high accuracy even with smallsample sizes and, therefore, can scale to very large graphs. Our code ispublicly available at https://github.com/dfdazac/grapes.

GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks