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

Disentangled Graph Convolutional Network (DisenGCN) is an encouragingframework to disentangle the latent factors arising in a real-world graph.However, it relies on disentangling information heavily from a local range(i.e., a node and its 1-hop neighbors), while the local information in manycases can be uneven and incomplete, hindering the interpretabiliy power andmodel performance of DisenGCN. In this paper\footnote{This paper is a lighterversion of \href{https://jingweio.github.io/assets/pdf/tnnls22.pdf}{"LearningDisentangled Graph Convolutional Networks Locally and Globally"} where theresults and analysis have been reworked substantially. Digital ObjectIdentifier \url{https://doi.org/10.1109/TNNLS.2022.3195336}.}, we introduce anovel Local and Global Disentangled Graph Convolutional Network (LGD-GCN) tocapture both local and global information for graph disentanglement. LGD-GCNperforms a statistical mixture modeling to derive a factor-aware latentcontinuous space, and then constructs different structures w.r.t. differentfactors from the revealed space. In this way, the global factor-specificinformation can be efficiently and selectively encoded via a message passingalong these built structures, strengthening the intra-factor consistency. Wealso propose a novel diversity promoting regularizer employed with the latentspace modeling, to encourage inter-factor diversity. Evaluations of theproposed LGD-GCN on the synthetic and real-world datasets show a betterinterpretability and improved performance in node classification over theexisting competitive models. Code is available at\url{https://github.com/jingweio/LGD-GCN}.

LGD-GCN: Local and Global Disentangled Graph Convolutional Networks