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

Spatiotemporal learning, which aims at extracting spatiotemporal correlationsfrom the collected spatiotemporal data, is a research hotspot in recent years.And considering the inherent graph structure of spatiotemporal data, recentworks focus on capturing spatial dependencies by utilizing Graph ConvolutionalNetworks (GCNs) to aggregate vertex features with the guidance of adjacencymatrices. In this paper, with extensive and deep-going experiments, wecomprehensively analyze existing spatiotemporal graph learning models andreveal that extracting adjacency matrices with carefully design strategies,which are viewed as the key of enhancing performance on graph learning, arelargely ineffective. Meanwhile, based on these experiments, we also discoverthat the aggregation itself is more important than the way that how verticesare aggregated. With these preliminary, a novel efficient Graph-Free Spatial(GFS) learning module based on layer normalization for capturing spatialcorrelations in spatiotemporal graph learning. The proposed GFS module can beeasily plugged into existing models for replacing all graph convolutioncomponents. Rigorous theoretical proof demonstrates that the time complexity ofGFS is significantly better than that of graph convolution operation. Extensiveexperiments verify the superiority of GFS in both the perspectives ofefficiency and learning effect in processing graph-structured data especiallyextreme large scale graph data.

Graph-Free Learning in Graph-Structured Data: A More Efficient and Accurate Spatiotemporal Learning Perspective