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

Recent advances in Graph Convolutional Neural Networks (GCNNs) have showntheir efficiency for non-Euclidean data on graphs, which often require a largeamount of labeled data with high cost. It it thus critical to learn graphfeature representations in an unsupervised manner in practice. To this end, wepropose a novel unsupervised learning of Graph Transformation EquivariantRepresentations (GraphTER), aiming to capture intrinsic patterns of graphstructure under both global and local transformations. Specifically, we allowto sample different groups of nodes from a graph and then transform themnode-wise isotropically or anisotropically. Then, we self-train arepresentation encoder to capture the graph structures by reconstructing thesenode-wise transformations from the feature representations of the original andtransformed graphs. In experiments, we apply the learned GraphTER to graphs of3D point cloud data, and results on point cloud segmentation/classificationshow that GraphTER significantly outperforms state-of-the-art unsupervisedapproaches and pushes greatly closer towards the upper bound set by the fullysupervised counterparts. The code is available at:https://github.com/gyshgx868/graph-ter.

GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformations