FR-Train: A mutual information-based approach to fair and robust training

02/24/2020
by   Yuji Roh, et al.
0

Trustworthy AI is a critical issue in machine learning where, in addition to training a model that is accurate, one must consider both fair and robust training in the presence of data bias and poisoning. However, the existing model fairness techniques mistakenly view poisoned data as an additional bias, resulting in severe performance degradation. To fix this problem, we propose FR-Train, which holistically performs fair and robust model training. We provide a mutual information-based interpretation of an existing adversarial training-based fairness-only method, and apply this idea to architect an additional discriminator that can identify poisoned data using a clean validation set and reduce its influence. In our experiments, FR-Train shows almost no decrease in fairness and accuracy in the presence of data poisoning by both mitigating the bias and defending against poisoning. We also demonstrate how to construct clean validation sets using crowdsourcing, and release new benchmark datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/13/2020

To be Robust or to be Fair: Towards Fairness in Adversarial Training

Adversarial training algorithms have been proven to be reliable to impro...
research
10/27/2021

Sample Selection for Fair and Robust Training

Fairness and robustness are critical elements of Trustworthy AI that nee...
research
01/15/2021

Responsible AI Challenges in End-to-end Machine Learning

Responsible AI is becoming critical as AI is widely used in our everyday...
research
09/15/2022

Improving Robust Fairness via Balance Adversarial Training

Adversarial training (AT) methods are effective against adversarial atta...
research
09/20/2023

Dr. FERMI: A Stochastic Distributionally Robust Fair Empirical Risk Minimization Framework

While training fair machine learning models has been studied extensively...
research
04/22/2019

Data Cleaning for Accurate, Fair, and Robust Models: A Big Data - AI Integration Approach

The wide use of machine learning is fundamentally changing the software ...
research
06/29/2022

Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale

The success of DNNs is driven by the counter-intuitive ability of over-p...

Please sign up or login with your details

Forgot password? Click here to reset