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

Meta-learning (ML) has emerged as a promising learning method under resourceconstraints such as few-shot learning. ML approaches typically propose amethodology to learn generalizable models. In this work-in-progress paper, weput the recent ML approaches to a stress test to discover their limitations.Precisely, we measure the performance of ML approaches for few-shot learningagainst increasing task complexity. Our results show a quick degradation in theperformance of initialization strategies for ML (MAML, TAML, and MetaSGD),while surprisingly, approaches that use an optimization strategy (MetaLSTM)perform significantly better. We further demonstrate the effectiveness of anoptimization strategy for ML (MetaLSTM++) trained in a MAML manner over a pureoptimization strategy. Our experiments also show that the optimizationstrategies for ML achieve higher transferability from simple to complex tasks.

Stress Testing of Meta-learning Approaches for Few-shot Learning