Few-Shot Learning With Class Imbalance

Mateusz Ochal, Massimiliano Patacchiola, Jose Vazquez, Amos Storkey, Sen Wang

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)
139 Downloads (Pure)

Abstract

Few-shot learning (FSL) algorithms are commonly trained through meta-learning (ML), which exposes models to batches of tasks sampled from a meta-dataset to mimic tasks seen during evaluation. However, the standard training procedures overlook the real-world dynamics where classes commonly occur at different frequencies. While it is generally understood that class imbalance harms the performance of supervised methods, limited research examines the impact of imbalance on the FSL evaluation task. Our analysis compares ten state-of-the-art ML and FSL methods on different imbalance distributions and rebalancing techniques. Our results reveal that: 1) some FSL methods display a natural disposition against imbalance while most other approaches produce a performance drop by up to 17% compared to the balanced task without the appropriate mitigation; 2) many ML algorithms will not automatically learn to balance from exposure to imbalanced training tasks; 3) classical rebalancing strategies, such as random oversampling, can still be very effective, leading to state-of-the-art performances and should not be overlooked.

Original languageEnglish
Pages (from-to)1348-1358
Number of pages11
JournalIEEE Transactions on Artificial Intelligence
Volume4
Issue number5
Early online date24 Jul 2023
DOIs
Publication statusPublished - Oct 2023

Keywords

  • Class imbalance
  • classification and regression
  • few-shot learning (FSL)
  • low-shot learning
  • meta learning (ML)

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Few-Shot Learning With Class Imbalance'. Together they form a unique fingerprint.

Cite this