DeepAI AI Chat
Log In Sign Up

Fair Meta-Learning For Few-Shot Classification

by   Chen Zhao, et al.

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.


page 1

page 2


Unfairness Discovery and Prevention For Few-Shot Regression

We study fairness in supervised few-shot meta-learning models that are s...

Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data

In this paper, we advocate for the study of fairness techniques in low d...

Fair Meta-Learning: Learning How to Learn Fairly

Data sets for fairness relevant tasks can lack examples or be biased acc...

Meta-Learning Initializations for Image Segmentation

While meta-learning approaches that utilize neural network representatio...

A Ransomware Triage Approach using a Task Memory based on Meta-Transfer Learning Framework

Solutions for rapid prioritization of different ransomware have been rai...

Predict Responsibly: Increasing Fairness by Learning To Defer

Machine learning systems, which are often used for high-stakes decisions...

Fairness-Aware Online Meta-learning

In contrast to offline working fashions, two research paradigms are devi...