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

In real-world scenarios, texts in a graph are often linked by multiplesemantic relations (e.g., papers in an academic graph are referenced by otherpublications, written by the same author, or published in the same venue),where text documents and their relations form a multiplex text-attributedgraph. Mainstream text representation learning methods use pretrained languagemodels (PLMs) to generate one embedding for each text unit, expecting that alltypes of relations between texts can be captured by these single-viewembeddings. However, this presumption does not hold particularly in multiplextext-attributed graphs. Along another line of work, multiplex graph neuralnetworks (GNNs) directly initialize node attributes as a feature vector fornode representation learning, but they cannot fully capture the semantics ofthe nodes' associated texts. To bridge these gaps, we propose METAG, a newframework for learning Multiplex rEpresentations on Text-Attributed Graphs. Incontrast to existing methods, METAG uses one text encoder to model the sharedknowledge across relations and leverages a small number of parameters perrelation to derive relation-specific representations. This allows the encoderto effectively capture the multiplex structures in the graph while alsopreserving parameter efficiency. We conduct experiments on nine downstreamtasks in five graphs from both academic and e-commerce domains, where METAGoutperforms baselines significantly and consistently. The code is available athttps://github.com/PeterGriffinJin/METAG.

Learning Multiplex Representations on Text-Attributed Graphs with One Language Model Encoder