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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Evolving temporal networks serve as the abstractions of many real-lifedynamic systems, e.g., social network and e-commerce. The purpose of temporalnetwork embedding is to map each node to a time-evolving low-dimension vectorfor downstream tasks, e.g., link prediction and node classification. Thedifficulty of temporal network embedding lies in how to utilize the topologyand time information jointly to capture the evolution of a temporal network. Inresponse to this challenge, we propose a temporal motif-preserving networkembedding method with bicomponent neighbor aggregation, named TME-BNA.Considering that temporal motifs are essential to the understanding of topologylaws and functional properties of a temporal network, TME-BNA constructsadditional edge features based on temporal motifs to explicitly utilize complextopology with time information. In order to capture the topology dynamics ofnodes, TME-BNA utilizes Graph Neural Networks (GNNs) to aggregate thehistorical and current neighbors respectively according to the timestamps ofconnected edges. Experiments are conducted on three public temporal networkdatasets, and the results show the effectiveness of TME-BNA.

TME-BNA: Temporal Motif-Preserving Network Embedding with Bicomponent Neighbor Aggregation