Fair Meta-Learning For Few-Shot Classification

TL;DR

This paper introduces a fair meta-learning approach for few-shot classification that reduces bias and improves fairness across tasks, while maintaining accuracy, by controlling decision boundary covariance during training.

Contribution

It proposes a novel fair meta-learning method that mitigates bias during meta-training, enhancing fairness and generalization in few-shot classification tasks.

Findings

Effectively reduces bias in model outputs.

Maintains high accuracy and fairness on unseen tasks.

Outperforms existing meta-learning algorithms in fairness metrics.

Abstract

Artificial intelligence nowadays plays an increasingly prominent role in our life since decisions that were once made by humans are now delegated to automated systems. A machine learning algorithm trained based on biased data, however, tends to make unfair predictions. Developing classification algorithms that are fair with respect to protected attributes of the data thus becomes an important problem. Motivated by concerns surrounding the fairness effects of sharing and few-shot machine learning tools, such as the Model Agnostic Meta-Learning framework, we propose a novel fair fast-adapted few-shot meta-learning approach that efficiently mitigates biases during meta-train by ensuring controlling the decision boundary covariance that between the protected variable and the signed distance from the feature vectors to the decision boundary. Through extensive experiments on two real-world image benchmarks over three state-of-the-art meta-learning algorithms, we empirically demonstrate that our proposed approach efficiently mitigates biases on model output and generalizes both accuracy and fairness to unseen tasks with a limited amount of training samples.