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/

Zendy Plus

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

Zendy Tools

Zendy Open

Modern graph neural networks (GNNs) use a message passing scheme and haveachieved great success in many fields. However, this recursive designinherently leads to excessive computation and memory requirements, making itnot applicable to massive real-world graphs. In this work, we propose theNeighbor2Seq to transform the hierarchical neighborhood of each node into asequence. This novel transformation enables the subsequent mini-batch trainingfor general deep learning operations, such as convolution and attention, thatare designed for grid-like data and are shown to be powerful in variousdomains. Therefore, our Neighbor2Seq naturally endows GNNs with the efficiencyand advantages of deep learning operations on grid-like data by precomputingthe Neighbor2Seq transformations. We evaluate our method on a massive graph,with more than 111 million nodes and 1.6 billion edges, as well as severalmedium-scale graphs. Results show that our proposed method is scalable tomassive graphs and achieves superior performance across massive andmedium-scale graphs. Our code is available athttps://github.com/divelab/Neighbor2Seq.

Neighbor2Seq: Deep Learning on Massive Graphs by Transforming Neighbors to Sequences