Semi-Supervised Few-Shot Learning with Prototypical Random Walks

Ahmed Ayyad, Yuchen Li, Raden Muaz, Shadi Albarqouni, Mohamed Elhoseiny

Research output: Contribution to conferencePaperpeer-review

6 Scopus citations

Abstract

Recent progress has shown that few-shot learning can be improved with access to unlabelled data, known as semi-supervised few-shot learning(SS-FSL).We introduce an SS-FSL approach, dubbed as Prototypical RandomWalk Networks(PRWN), built on top of Prototypical Networks (PN). We develop a random walk semisupervised loss that enables the network to learn representations that are compact and well-separated. Our work is related to the very recent development of graph-based approaches for few-shot learning. However, we show that compact and well-separated class representations can be achieved by modeling our prototypical random walk notion without needing additional graph-NN parameters or requiring a transductive setting where a collective test set is provided. Our model outperforms baselines in most benchmarks with significant improvements in some cases. Our model, trained with 40% of the data as labeled, compares.

Original languageEnglish (US)
Pages45-57
Number of pages13
StatePublished - 2021
Event2021 AAAI Workshop on Meta-Learning and MetaDL Challenge - Virtual, Online
Duration: Feb 9 2021 → …

Conference

Conference2021 AAAI Workshop on Meta-Learning and MetaDL Challenge
CityVirtual, Online
Period02/9/21 → …

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Semi-Supervised Few-Shot Learning with Prototypical Random Walks'. Together they form a unique fingerprint.

Cite this