arXiv research

A new method SLIDE ensures fairness in AI models.

Paper proposes a modified fairness constraint to address shortcomings of counterfactual fairness.

Algorithm identifies intended fairness constraints from expert demonstrations for fair clustering.

In classification models fairness can be ensured by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimiz…

Fair Mixup improves fairness in classifiers by interpolating between groups.

Algorithm improves movie recommendation efficiency with fairness constraints.

We reformulate data-dependent constraints to ensure they are always met with high probability.

This work optimizes model performance while ensuring fairness through AUC constraints.

Meta-theorems validate fair regression algorithms under demographic parity constraints.

New method certifies individual fairness in representations.

Developing classification algorithms that are fair with respect to sensitive attributes of the data has become an important problem due to the growing deployment of classification algorithms in various social contexts. Several recent works have focused on fairness with respect to a specific metric, modeled the correspo…

The paper tackles fair set-valued classification under demographic parity constraints.

A new bias score method optimizes fairness in classification.

New method for private learning with fairness constraints.

Kearns et al. [2018] recently proposed a notion of rich subgroup fairness intended to bridge the gap between statistical and individual notions of fairness. Rich subgroup fairness picks a statistical fairness constraint (say, equalizing false positive rates across protected groups), but then asks that this constraint h…

In this paper, we study correlation clustering under fairness constraints. Fair variants of $k$-median and $k$-center clustering have been studied recently, and approximation algorithms using a notion called fairlet decomposition have been proposed. We obtain approximation algorithms for fair correlation clustering und…

We address the problem of algorithmic fairness: ensuring that sensitive variables do not unfairly influence the outcome of a classifier. We present an approach based on empirical risk minimization, which incorporates a fairness constraint into the learning problem. It encourages the conditional risk of the learned clas…

OTF uses optimal transport to measure classifier fairness.

Algorithm samples fair rankings to ensure individual fairness while maintaining group fairness.

Fairness-aware classification is receiving increasing attention in the machine learning fields. Recently research proposes to formulate the fairness-aware classification as constrained optimization problems. However, several limitations exist in previous works due to the lack of a theoretical framework for guiding the …

Study fairness in intervention to maximize outcomes.

Recently there has been sustained interest in modifying prediction algorithms to satisfy fairness constraints. These constraints are typically complex nonlinear functionals of the observed data distribution. Focusing on the path-specific causal constraints proposed by Nabi and Shpitser (2018), we introduce new theoreti…

Proposes a framework for partially fair machine learning models.

A new method for fair representation learning using PLS.

BAICS identifies best arm with fairness constraints on subpopulations.

Doubly fair dynamic pricing ensures equal prices for different groups over time.

Proposes a method to create fair ITRs that balance value and fairness.

This paper addresses dynamic price discrimination with fairness constraints.

Many applications of AI involve scoring individuals using a learned function of their attributes. These predictive risk scores are then used to take decisions based on whether the score exceeds a certain threshold, which may vary depending on the context. The level of delegation granted to such systems in critical appl…

Proposes a method to enforce fairness in machine learning models without sensitive data.

Bayesian optimization framework for fair machine learning models.

The study connects fairness constraints with optimal transport to derive new insights in classification.

FCA improves fair clustering by optimizing utility and fairness.

Develops methods for fair classification under linear disparity constraints.

We consider settings in which the right notion of fairness is not captured by simple mathematical definitions (such as equality of error rates across groups), but might be more complex and nuanced and thus require elicitation from individual or collective stakeholders. We introduce a framework in which pairs of individ…

Ditto improves fairness and robustness in federated learning.

Paper develops a fair pricing algorithm for dynamic settings with uncertain demand.

Learning high-quality node embeddings is a key building block for machine learning models that operate on graph data, such as social networks and recommender systems. However, existing graph embedding techniques are unable to cope with fairness constraints, e.g., ensuring that the learned representations do not correla…

New algorithm speeds up fair clustering by 12x.

New framework for fair ranking with noisy protected attributes.

New classifiers ensure fairness by adjusting a base classifier's operating characteristics.

FairTrade uses variational inference to create fair predictions in causal models.

The potential for learned models to amplify existing societal biases has been broadly recognized. Fairness-aware classifier constraints, which apply equality metrics of performance across subgroups defined on sensitive attributes such as race and gender, seek to rectify inequity but can yield non-uniform degradation in…

HyperFair integrates fairness in recommender systems using probabilistic soft logic.

A new ML method teaches constraints directly to models.

Fair machine learning models can be vulnerable to adversarial attacks that reduce their accuracy and fairness.

Classifiers and rating scores are prone to implicitly codifying biases, which may be present in the training data, against protected classes (i.e., age, gender, or race). So it is important to understand how to design classifiers and scores that prevent discrimination in predictions. This paper develops computationally…

Group fairness is an important concern for machine learning researchers, developers, and regulators. However, the strictness to which models must be constrained to be considered fair is still under debate. The focus of this work is on constraining the expected outcome of subpopulations in kernel regression and, in part…