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

This paper studies the problem of cross-network node classification toovercome the insufficiency of labeled data in a single network. It aims toleverage the label information in a partially labeled source network to assistnode classification in a completely unlabeled or partially labeled targetnetwork. Existing methods for single network learning cannot solve this problemdue to the domain shift across networks. Some multi-network learning methodsheavily rely on the existence of cross-network connections, thus areinapplicable for this problem. To tackle this problem, we propose a novel\textcolor{black}{graph} transfer learning framework AdaGCN by leveraging thetechniques of adversarial domain adaptation and graph convolution. It consistsof two components: a semi-supervised learning component and an adversarialdomain adaptation component. The former aims to learn class discriminative noderepresentations with given label information of the source and target networks,while the latter contributes to mitigating the distribution divergence betweenthe source and target domains to facilitate knowledge transfer. Extensiveempirical evaluations on real-world datasets show that AdaGCN can successfullytransfer class information with a low label rate on the source network and asubstantial divergence between the source and target domains. The source codefor reproducing the experimental results is available athttps://github.com/daiquanyu/AdaGCN.

Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolution