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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep learning has demonstrated abilities to learn complex structures, butthey can be restricted by available data. Recently, Consensus Networks (CNs)were proposed to alleviate data sparsity by utilizing features from multiplemodalities, but they too have been limited by the size of labeled data. In thispaper, we extend CN to Transductive Consensus Networks (TCNs), suitable forsemi-supervised learning. In TCNs, different modalities of input are compressedinto latent representations, which we encourage to become indistinguishableduring iterative adversarial training. To understand TCNs two mechanisms,consensus and classification, we put forward its three variants in ablationstudies on these mechanisms. To further investigate TCN models, we treat thelatent representations as probability distributions and measure theirsimilarities as the negative relative Jensen-Shannon divergences. We show thata consensus state beneficial for classification desires a stable but imperfectsimilarity between the representations. Overall, TCNs outperform or align withthe best benchmark algorithms given 20 to 200 labeled samples on the BankMarketing and the DementiaBank datasets.

Semi-supervised classification by reaching consensus among modalities