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

Partial domain adaptation (PDA), in which we assume the target label space isincluded in the source label space, is a general version of standard domainadaptation. Since the target label space is unknown, the main challenge of PDAis to reduce the learning impact of irrelevant source samples, named outliers,which do not belong to the target label space. Although existing partial domainadaptation methods effectively down-weigh outliers' importance, they do notconsider data structure of each domain and do not directly align the featuredistributions of the same class in the source and target domains, which maylead to misalignment of category-level distributions. To overcome theseproblems, we propose a graph partial domain adaptation (GPDA) network, whichexploits Graph Convolutional Networks for jointly considering data structureand the feature distribution of each class. Specifically, we propose a labelrelational graph to align the distributions of the same category in two domainsand introduce moving average centroid separation for learning networks from thelabel relational graph. We demonstrate that considering data structure and thedistribution of each category is effective for PDA and our GPDA networkachieves state-of-the-art performance on the Digit and Office-31 datasets.

Partial Domain Adaptation Using Graph Convolutional Networks