Null-sampling for Interpretable and Fair Representations

2020-08-12 · ECCV 2020 8 · Thomas Kehrenberg, Myles Bartlett, Oliver Thomas, Novi Quadrianto

We propose to learn invariant representations, in the data domain, to achieve interpretability in algorithmic fairness. Invariance implies a selectivity for high level, relevant correlations w.r.t. class label annotations, and a robustness to irrelevant correlations with protected characteristics such as race or gender. We introduce a non-trivial setup in which the training set exhibits a strong bias such that class label annotations are irrelevant and spurious correlations cannot be distinguished. To address this problem, we introduce an adversarially trained model with a null-sampling procedure to produce invariant representations in the data domain. To enable disentanglement, a partially-labelled representative set is used. By placing the representations into the data domain, the changes made by the model are easily examinable by human auditors. We show the effectiveness of our method on both image and tabular datasets: Coloured MNIST, the CelebA and the Adult dataset.

📄 PDF Abstract BibTeX arXiv:2008.05248

Code (1)

predictive-analytics-lab/nifr 공식 구현 pytorch

Tasks

Disentanglement Fairness Image Classification

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection

2020-04-16 · ACL 2020 6 · Shauli Ravfogel, Yanai Elazar, Hila Gonen, Michael Twiton 외

The ability to control for the kinds of information encoded in neural representation has a variety of use cases, especially in light of the challenge of interpreting these models. We present Iterative Null-space Projecti…

Fairness Multi-class Classification Word Embeddings

Learning Interpretable Fair Representations

2024-06-24 · Tianhao Wang, Zana Buçinca, Zilin Ma

Numerous approaches have been recently proposed for learning fair representations that mitigate unfair outcomes in prediction tasks. A key motivation for these methods is that the representations can be used by third par…

Prediction Representation Learning

Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization

2026-08-24 · Sunhee Hwang arxiv

Deep learning models often produce performance disparities across demographic groups, due to the training data imbalance with respect to sensitive attributes such as gender or age. To address this problem, existing work …

Representation Learning

Fairness constraint in Structural Econometrics and Application to fair estimation using Instrumental Variables

2022-02-16 · Samuele Centorrino, Jean-Pierre Florens, Jean-Michel Loubes

A supervised machine learning algorithm determines a model from a learning sample that will be used to predict new observations. To this end, it aggregates individual characteristics of the observations of the learning s…

BIG-bench Machine Learning Econometrics Fairness

Meritocratic Fairness via $K$-Shapley Values in Budgeted Combinatorial Bandits with Full-Bandit Feedback

2026-05-01 · Shradha Sharma, Swapnil Dhamal, Shweta Jain arxiv

We study meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback, where a learner selects at most $K$ arms per time step and observes only the noisy aggregate reward of the selected …

Multi-Armed Bandits Federated Learning