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

With the growing significance of graphs as an effective representation ofdata in numerous applications, efficient graph analysis using modern machinelearning is receiving a growing level of attention. Deep learning approachesoften operate over the entire adjacency matrix -- as the input and intermediatenetwork layers are all designed in proportion to the size of the adjacencymatrix -- leading to intensive computation and large memory requirements as thegraph size increases. It is therefore desirable to identify efficient measuresto reduce both run-time and memory requirements allowing for the analysis ofthe largest graphs possible. The use of reduced precision operations within theforward and backward passes of a deep neural network along with novelspecialised hardware in modern GPUs can offer promising avenues towardsefficiency. In this paper, we provide an in-depth exploration of the use ofreduced-precision operations, easily integrable into the highly popular PyTorchframework, and an analysis of the effects of Tensor Cores on graphconvolutional neural networks. We perform an extensive experimental evaluationof three GPU architectures and two widely-used graph analysis tasks (vertexclassification and link prediction) using well-known benchmark andsynthetically generated datasets. Thus allowing us to make importantobservations on the effects of reduced-precision operations and Tensor Cores oncomputational and memory usage of graph convolutional neural networks -- oftenneglected in the literature.

Not Half Bad: Exploring Half-Precision in Graph Convolutional Neural Networks