Related papers: Fair Classification via Domain Adaptation: A Dual …
Machine learning based systems are reaching society at large and in many aspects of everyday life. This phenomenon has been accompanied by concerns about the ethical issues that may arise from the adoption of these technologies. ML fairness…
In recent years, a growing body of work has emerged on how to learn machine learning models under fairness constraints, often expressed with respect to some sensitive attributes. In this work, we consider the setting in which an adversary…
Most existing fair classifiers rely on sensitive attributes to achieve fairness. However, for many scenarios, we cannot obtain sensitive attributes due to privacy and legal issues. The lack of sensitive attributes challenges many existing…
Effective machine learning models can automatically learn useful information from a large quantity of data and provide decisions in a high accuracy. These models may, however, lead to unfair predictions in certain sense among the population…
Fairness-aware machine learning has attracted a surge of attention in many domains, such as online advertising, personalized recommendation, and social media analysis in web applications. Fairness-aware machine learning aims to eliminate…
With growing awareness of societal impact of artificial intelligence, fairness has become an important aspect of machine learning algorithms. The issue is that human biases towards certain groups of population, defined by sensitive features…
Domain adaptation is a sub-field of machine learning that involves transferring knowledge from a source domain to perform the same task in the target domain. It is a typical challenge in machine learning that arises, e.g., when data is…
In medical image diagnosis, fairness has become increasingly crucial. Without bias mitigation, deploying unfair AI would harm the interests of the underprivileged population and potentially tear society apart. Recent research addresses…
Domain-adapted sentiment classification refers to training on a labeled source domain to well infer document-level sentiment on an unlabeled target domain. Most existing relevant models involve a feature extractor and a sentiment…
How can we learn a classifier that is "fair" for a protected or sensitive group, when we do not know if the input to the classifier belongs to the protected group? How can we train such a classifier when data on the protected group is…
A central goal of algorithmic fairness is to reduce bias in automated decision making. An unavoidable tension exists between accuracy gains obtained by using sensitive information (e.g., gender or ethnic group) as part of a statistical…
Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training and deployment data distributions are identical, which is often not true in…
The endeavor to preserve the generalization of a fair and invariant classifier across domains, especially in the presence of distribution shifts, becomes a significant and intricate challenge in machine learning. In response to this…
Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race. To avoid disparate treatment, sensitive attributes…
As machine learning (ML) based systems are adopted in domains such as law enforcement, criminal justice, finance, hiring and admissions, ensuring the fairness of ML aided decision-making is becoming increasingly important. In this paper, we…
Deep learning-based recognition systems are deployed at scale for several real-world applications that inevitably involve our social life. Although being of great support when making complex decisions, they might capture spurious data…
We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation…
Counterfactual fairness is an approach to AI fairness that tries to make decisions based on the outcomes that an individual with some kind of sensitive status would have had without this status. This paper proposes Double Machine Learning…
In contrast to offline working fashions, two research paradigms are devised for online learning: (1) Online Meta Learning (OML) learns good priors over model parameters (or learning to learn) in a sequential setting where tasks are revealed…
The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an unlabeled target domain, with a similar but different data distribution. Most deep learning approaches to…