Fairness

Boosting fair machine learning’s robustness against noisy labels, this work introduces a novel label-spreading method, achieving state-of-the-art worst-group accuracy.

Repeated cake-cutting game reveals that strategic players can exploit myopic opponents, but equitable outcomes are achievable through specific strategies.

DeNetDM uses network depth modulation to automatically debiase image classifiers without bias annotations or data augmentation, improving accuracy by 5%.

This paper proposes a novel method to achieve optimal counterfactual fairness in machine learning models while minimizing predictive performance degradation.

This paper introduces AFCP, a novel conformal inference method that generates prediction sets with valid coverage conditional on adaptively selected features, achieving a practical balance between eff…

Boost classifier stability with the novel inflated argmax, guaranteeing reliable multiclass classification without distributional assumptions!

AI systems acquire bias during training, impacting accuracy across sub-populations. This research unveils bias’s dynamic nature, revealing how classifier preferences shift over time, influenced by dat…

AI models retraining with model-annotated data incorporating human strategic responses can lead to unexpected outcomes, potentially reducing the proportion of agents with positive labels over time, wh…

Node Injection-based Fairness Attack (NIFA) reveals GNNs’ vulnerability to realistic fairness attacks by injecting a small percentage of nodes, significantly undermining fairness even in fairness-awar…

This paper introduces a computationally efficient method to approximate the optimal accuracy-fairness trade-off curve for various datasets, providing rigorous statistical guarantees and quantifying un…

A novel post-processing framework, based on a d-dimensional generalization of the Neyman-Pearson lemma, optimally solves multi-objective learn-to-defer problems under various constraints, improving co…

This paper introduces Bias-Conditioned Self-Influence (BCSI) for precise bias-conflicting sample detection and model rectification, enhancing fairness in machine learning.

Debunking a common myth, this paper proves that AUPRC is not superior to AUROC for imbalanced datasets, and in fact, can worsen algorithmic bias.