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

Recurrent neural network (RNN) and self-attention mechanism (SAM) are the defacto methods to extract spatial-temporal information for temporal graphlearning. Interestingly, we found that although both RNN and SAM could lead toa good performance, in practice neither of them is always necessary. In thispaper, we propose GraphMixer, a conceptually and technically simplearchitecture that consists of three components: (1) a link-encoder that is onlybased on multi-layer perceptrons (MLP) to summarize the information fromtemporal links, (2) a node-encoder that is only based on neighbor mean-poolingto summarize node information, and (3) an MLP-based link classifier thatperforms link prediction based on the outputs of the encoders. Despite itssimplicity, GraphMixer attains an outstanding performance on temporal linkprediction benchmarks with faster convergence and better generalizationperformance. These results motivate us to rethink the importance of simplermodel architecture.

Do We Really Need Complicated Model Architectures For Temporal Networks?