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

Graph neural networks (GNNs) have been attracting increasing popularity dueto their simplicity and effectiveness in a variety of fields. However, a largenumber of labeled data is generally required to train these networks, whichcould be very expensive to obtain in some domains. In this paper, we studyactive learning for GNNs, i.e., how to efficiently label the nodes on a graphto reduce the annotation cost of training GNNs. We formulate the problem as asequential decision process on graphs and train a GNN-based policy network withreinforcement learning to learn the optimal query strategy. By jointly trainingon several source graphs with full labels, we learn a transferable activelearning policy which can directly generalize to unlabeled target graphs.Experimental results on multiple datasets from different domains prove theeffectiveness of the learned policy in promoting active learning performance inboth settings of transferring between graphs in the same domain and acrossdifferent domains.

Graph Policy Network for Transferable Active Learning on Graphs