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

Dynamic graph representation learning is growing as a trending yetchallenging research task owing to the widespread demand for graph dataanalysis in real world applications. Despite the encouraging performance ofmany recent works that build upon recurrent neural networks (RNNs) and graphneural networks (GNNs), they fail to explicitly model the impact of edgetemporal states on node features over time slices. Additionally, they arechallenging to extract global structural features because of the inherentover-smoothing disadvantage of GNNs, which further restricts the performance.In this paper, we propose a recurrent difference graph transformer (RDGT)framework, which firstly assigns the edges in each snapshot with various typesand weights to illustrate their specific temporal states explicitly, then astructure-reinforced graph transformer is employed to capture the temporal noderepresentations by a recurrent learning paradigm. Experimental results on fourreal-world datasets demonstrate the superiority of RDGT for discrete dynamicgraph representation learning, as it consistently outperforms competing methodsin dynamic link prediction tasks.

Recurrent Transformer for Dynamic Graph Representation Learning with Edge Temporal States