相关论文: Proxy Non-Discrimination in Data-Driven Systems

Proxy-based race inference is increasingly used to conduct fairness assessments when protected-class data are unavailable or legally restricted -- most prominently in U.S. fair-lending enforcement, and now explicitly contemplated in…

The problem of algorithmic bias in machine learning has gained a lot of attention in recent years due to its concrete and potentially hazardous implications in society. In much the same manner, biases can also alter modern industrial and…

Algorithmic approaches endow deep learning systems with implicit bias that helps them generalize even in over-parametrized settings. In this paper, we focus on understanding such a bias induced in learning through dropout, a popular…

Fairness-aware learning aims to mitigate discrimination against specific protected social groups (e.g., those categorized by gender, ethnicity, age) while minimizing predictive performance loss. Despite efforts to improve fairness in…

While data-driven predictive models are a strictly technological construct, they may operate within a social context in which benign engineering choices entail implicit, indirect and unexpected real-life consequences. Fairness of such…

Bias-transforming methods of fairness-aware machine learning aim to correct a non-neutral status quo with respect to a protected attribute (PA). Current methods, however, lack an explicit formulation of what drives non-neutrality. We…

We address the problem of reward hacking, where maximising a proxy reward does not necessarily increase the true reward. This is a key concern for Large Language Models (LLMs), as they are often fine-tuned on human preferences that may not…

Existing metric learning losses can be categorized into two classes: pair-based and proxy-based losses. The former class can leverage fine-grained semantic relations between data points, but slows convergence in general due to its high…

Prediction-based decision-making systems are becoming increasingly prevalent in various domains. Previous studies have demonstrated that such systems are vulnerable to runaway feedback loops, e.g., when police are repeatedly sent back to…

Controversies around race and machine learning have sparked debate among computer scientists over how to design machine learning systems that guarantee fairness. These debates rarely engage with how racial identity is embedded in our social…

We propose a fairness-aware learning framework that mitigates intersectional subgroup bias associated with protected attributes. Prior research has primarily focused on mitigating one kind of bias by incorporating complex fairness-driven…

Algorithmic discrimination is an important aspect when data is used for predictive purposes. This paper analyzes the relationships between discrimination and classification, data set partitioning, and decision models, as well as…

3D softwares are now capable of producing highly realistic images that look nearly indistinguishable from the real images. This raises the question: can real datasets be enhanced with 3D rendered data? We investigate this question. In this…

Machine learning models have demonstrated promising performance in many areas. However, the concerns that they can be biased against specific demographic groups hinder their adoption in high-stake applications. Thus, it is essential to…

Why do biased predictions arise? What interventions can prevent them? We evaluate 8.2 million algorithmic predictions of math performance from $\approx$400 AI engineers, each of whom developed an algorithm under a randomly assigned…

When analyzing the behavior of machine learning algorithms, it is important to identify specific data subgroups for which the considered algorithm shows different performance with respect to the entire dataset. The intervention of domain…

As the data-driven decision process becomes dominating for industrial applications, fairness-aware machine learning arouses great attention in various areas. This work proposes fairness penalties learned by neural networks with a simple…

Fairness aware data mining (FADM) aims to prevent algorithms from discriminating against protected groups. The literature has come to an impasse as to what constitutes explainable variability as opposed to discrimination. This distinction…

Fairness-aware machine learning has recently attracted various communities to mitigate discrimination against certain societal groups in data-driven tasks. For fair supervised learning, particularly in pre-processing, there have been two…

Machine learning models are often personalized with categorical attributes that are protected, sensitive, self-reported, or costly to acquire. In this work, we show models that are personalized with group attributes can reduce performance…