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

While there have been many studies on hardware acceleration for deep learningon images, there has been a rather limited focus on accelerating deep learningapplications involving graphs. The unique characteristics of graphs, such asthe irregular memory access and dynamic parallelism, impose several challengeswhen the algorithm is mapped to a CPU or GPU. To address these challenges whileexploiting all the available sparsity, we propose a flexible architecturecalled SPA-GCN for accelerating Graph Convolutional Networks (GCN), the corecomputation unit in deep learning algorithms on graphs. The architecture isspecialized for dealing with many small graphs since the graph size has asignificant impact on design considerations. In this context, we use SimGNN, aneural-network-based graph matching algorithm, as a case study to demonstratethe effectiveness of our architecture. The experimental results demonstratethat SPA-GCN can deliver a high speedup compared to a multi-core CPUimplementation and a GPU implementation, showing the efficiency of our design.

SPA-GCN: Efficient and Flexible GCN Accelerator with an Application for Graph Similarity Computation