Imbalanced learning is a machine learning setting where the algorithm learns from an experience dataset $$E$$ that is imbalanced with respect to the distribution of the target variable $$y$$.

University of Notre Dame

Google

1)	Weakly Supervised Learning

2)	Imbalanced Learning

3)	Transfer Learning

4)	Meta Learning

Learning Problem Relevant to Few-Shot Learning

Wang, Y., Yao, Q., Kwok, J. T., & Ni, L. M. (2020). Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur), 53(3), 1-34.

Generalizing from a Few Examples: A Survey on Few-Shot Learning

Weakly supervised learning learns from E with limited supervised data, such as incomplete, inaccurate, inexact or noisy supervised information.

Weakly Supervised Learning

Imbalanced Learning

Transfer Learning transfer the learned knowledge from one task/source with abundant training data to the current task/source with limited training data. 

Transfer Learning

Meta learning improves learning performance by first using meta-model to extract knowledge from meta data, and then aggregating meta models for the current task using task-specific information.

Learn Before

Related