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

A class of recent semi-supervised learning (SSL) methods heavily rely ondomain-specific data augmentations. In contrast, generative SSL methods involveunsupervised learning based on generative models by either joint-training orpre-training, and are more appealing from the perspective of beingdomain-agnostic, since they do not inherently require data augmentations.Joint-training estimates the joint distribution of observations and labels,while pre-training is taken over observations only. Recently, energy-basedmodels (EBMs) have achieved promising results for generative modeling.Joint-training via EBMs for SSL has been explored with encouraging resultsacross different data modalities. In this paper, we make two contributions.First, we explore pre-training via EBMs for SSL and compare it tojoint-training. Second, a suite of experiments are conducted over domains ofimage classification and natural language labeling to give a realistic wholepicture of the performances of EBM based SSL methods. It is found thatjoint-training EBMs outperform pre-training EBMs marginally but nearlyconsistently.

An empirical study of domain-agnostic semi-supervised learning via energy-based models: joint-training and pre-training