Domain Adaptation meets Individual Fairness. And they get along
- URL: http://arxiv.org/abs/2205.00504v2
- Date: Sat, 15 Oct 2022 13:00:00 GMT
- Title: Domain Adaptation meets Individual Fairness. And they get along
- Authors: Debarghya Mukherjee, Felix Petersen, Mikhail Yurochkin, Yuekai Sun
- Abstract summary: We show that algorithmic fairness interventions can help machine learning models overcome distribution shifts.
In particular, we show that enforcing suitable notions of individual fairness (IF) can improve the out-of-distribution accuracy of ML models.
- Score: 48.95808607591299
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Many instances of algorithmic bias are caused by distributional shifts. For
example, machine learning (ML) models often perform worse on demographic groups
that are underrepresented in the training data. In this paper, we leverage this
connection between algorithmic fairness and distribution shifts to show that
algorithmic fairness interventions can help ML models overcome distribution
shifts, and that domain adaptation methods (for overcoming distribution shifts)
can mitigate algorithmic biases. In particular, we show that (i) enforcing
suitable notions of individual fairness (IF) can improve the
out-of-distribution accuracy of ML models under the covariate shift assumption
and that (ii) it is possible to adapt representation alignment methods for
domain adaptation to enforce individual fairness. The former is unexpected
because IF interventions were not developed with distribution shifts in mind.
The latter is also unexpected because representation alignment is not a common
approach in the individual fairness literature.
Related papers
- Dr. FERMI: A Stochastic Distributionally Robust Fair Empirical Risk
Minimization Framework [12.734559823650887]
In the presence of distribution shifts, fair machine learning models may behave unfairly on test data.
Existing algorithms require full access to data and cannot be used when small batches are used.
This paper proposes the first distributionally robust fairness framework with convergence guarantees that do not require knowledge of the causal graph.
arXiv Detail & Related papers (2023-09-20T23:25:28Z) - A Differentiable Distance Approximation for Fairer Image Classification [31.471917430653626]
We propose a differentiable approximation of the variance of demographics, a metric that can be used to measure the bias, or unfairness, in an AI model.
Our approximation can be optimised alongside the regular training objective which eliminates the need for any extra models during training.
We demonstrate that our approach improves the fairness of AI models in varied task and dataset scenarios.
arXiv Detail & Related papers (2022-10-09T23:02:18Z) - How Robust is Your Fairness? Evaluating and Sustaining Fairness under
Unseen Distribution Shifts [107.72786199113183]
We propose a novel fairness learning method termed CUrvature MAtching (CUMA)
CUMA achieves robust fairness generalizable to unseen domains with unknown distributional shifts.
We evaluate our method on three popular fairness datasets.
arXiv Detail & Related papers (2022-07-04T02:37:50Z) - Transferring Fairness under Distribution Shifts via Fair Consistency
Regularization [15.40257564187799]
We study how to transfer model fairness under distribution shifts, a widespread issue in practice.
Inspired by the success of self-training in transferring accuracy under domain shifts, we derive a sufficient condition for transferring group fairness.
arXiv Detail & Related papers (2022-06-26T06:19:56Z) - Fairness Transferability Subject to Bounded Distribution Shift [5.62716254065607]
Given an algorithmic predictor that is "fair" on some source distribution, will it still be fair on an unknown target distribution that differs from the source within some bound?
We study the transferability of statistical group fairness for machine learning predictors subject to bounded distribution shifts.
arXiv Detail & Related papers (2022-05-31T22:16:44Z) - Predicting with Confidence on Unseen Distributions [90.68414180153897]
We connect domain adaptation and predictive uncertainty literature to predict model accuracy on challenging unseen distributions.
We find that the difference of confidences (DoC) of a classifier's predictions successfully estimates the classifier's performance change over a variety of shifts.
We specifically investigate the distinction between synthetic and natural distribution shifts and observe that despite its simplicity DoC consistently outperforms other quantifications of distributional difference.
arXiv Detail & Related papers (2021-07-07T15:50:18Z) - KL Guided Domain Adaptation [88.19298405363452]
Domain adaptation is an important problem and often needed for real-world applications.
A common approach in the domain adaptation literature is to learn a representation of the input that has the same distributions over the source and the target domain.
We show that with a probabilistic representation network, the KL term can be estimated efficiently via minibatch samples.
arXiv Detail & Related papers (2021-06-14T22:24:23Z) - Learning Invariant Representations and Risks for Semi-supervised Domain
Adaptation [109.73983088432364]
We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA)
We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
arXiv Detail & Related papers (2020-10-09T15:42:35Z) - Estimating Generalization under Distribution Shifts via Domain-Invariant
Representations [75.74928159249225]
We use a set of domain-invariant predictors as a proxy for the unknown, true target labels.
The error of the resulting risk estimate depends on the target risk of the proxy model.
arXiv Detail & Related papers (2020-07-06T17:21:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.