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

In few-shot domain adaptation (FDA), classifiers for the target domain aretrained with accessible labeled data in the source domain (SD) and few labeleddata in the target domain (TD). However, data usually contain privateinformation in the current era, e.g., data distributed on personal phones.Thus, the private information will be leaked if we directly access data in SDto train a target-domain classifier (required by FDA methods). In this paper,to thoroughly prevent the privacy leakage in SD, we consider a very challengingproblem setting, where the classifier for the TD has to be trained using fewlabeled target data and a well-trained SD classifier, named few-shot hypothesisadaptation (FHA). In FHA, we cannot access data in SD, as a result, the privateinformation in SD will be protected well. To this end, we propose a targetorientated hypothesis adaptation network (TOHAN) to solve the FHA problem,where we generate highly-compatible unlabeled data (i.e., an intermediatedomain) to help train a target-domain classifier. TOHAN maintains two deepnetworks simultaneously, where one focuses on learning an intermediate domainand the other takes care of the intermediate-to-target distributionaladaptation and the target-risk minimization. Experimental results show thatTOHAN outperforms competitive baselines significantly.

TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation