DeepAI AI Chat
Log In Sign Up

Explainability for fair machine learning

by   Tom Begley, et al.

As the decisions made or influenced by machine learning models increasingly impact our lives, it is crucial to detect, understand, and mitigate unfairness. But even simply determining what "unfairness" should mean in a given context is non-trivial: there are many competing definitions, and choosing between them often requires a deep understanding of the underlying task. It is thus tempting to use model explainability to gain insights into model fairness, however existing explainability tools do not reliably indicate whether a model is indeed fair. In this work we present a new approach to explaining fairness in machine learning, based on the Shapley value paradigm. Our fairness explanations attribute a model's overall unfairness to individual input features, even in cases where the model does not operate on sensitive attributes directly. Moreover, motivated by the linearity of Shapley explainability, we propose a meta algorithm for applying existing training-time fairness interventions, wherein one trains a perturbation to the original model, rather than a new model entirely. By explaining the original model, the perturbation, and the fair-corrected model, we gain insight into the accuracy-fairness trade-off that is being made by the intervention. We further show that this meta algorithm enjoys both flexibility and stability benefits with no loss in performance.


page 1

page 2

page 3

page 4


Superhuman Fairness

The fairness of machine learning-based decisions has become an increasin...

Fairness and Explainability: Bridging the Gap Towards Fair Model Explanations

While machine learning models have achieved unprecedented success in rea...

Fairness and Robustness of Contrasting Explanations

Fairness and explainability are two important and closely related requir...

Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models

Motivations for methods in explainable artificial intelligence (XAI) oft...

Gradient Frequency Modulation for Visually Explaining Video Understanding Models

In many applications, it is essential to understand why a machine learni...

The Bouncer Problem: Challenges to Remote Explainability

The concept of explainability is envisioned to satisfy society's demands...

Fairer and more accurate, but for whom?

Complex statistical machine learning models are increasingly being used ...