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

Learning with limited labelled data, such as few-shot learning, meta-learningor transfer learning, aims to effectively train a model using only small amountof labelled samples. However, these approaches were observed to be excessivelysensitive to the effects of uncontrolled randomness caused by non-determinismin the training process. The randomness negatively affects the stability of themodels, leading to large variance in results across training runs. When suchinstability is disregarded, it can unintentionally, but unfortunately alsointentionally, create an imaginary perception of research progress. Recently,this area started to attract a research attention and the number of relevantstudies is continuously growing. In this survey, we provide a comprehensiveoverview of 134 papers addressing the effects of randomness on the stability oflearning with limited labelled data. We distinguish between four main tasksaddressed in the papers (investigate/evaluate; determine; mitigate;benchmark/compare/report randomness effects), providing findings for each one.Furthermore, we identify and discuss seven challenges and open problemstogether with possible directions to facilitate further research. The ultimategoal of this survey is to emphasise the importance of this growing researcharea, which so far has not received appropriate level of attention.

On the Effects of Randomness on Stability of Learning with Limited Labelled Data: A Systematic Literature Review