• Fair exposure ≠ fair outcomes. Visibility in rankings does not guarantee equitable shortlisting in online recruitment. • Human and task factors matter. Recruiter behavior, task design, and candidate cues influence fairness beyond algorithms, as we show in user studies. • Design implications. Our findings translate into practical implications for model evaluations, interfaces, and recruiter practices to support equity. Personnel recruitment is increasingly mediated by Applicant Tracking Systems (ATS), which rank candidates for job positions, making them a central decision-support tool in modern Human Resources (HR) processes. Often framed as an information retrieval (IR) problem, the ranking of candidates in ATS is typically driven by relevance to the job position, with algorithms sorting applicants according to a set of predefined criteria. In recent years, fairness-aware ranking methods have emerged to mitigate the risk of indirect discrimination, where the ordering of candidates may inadvertently favor one demographic group over another. These approaches are inspired by browsing models developed for web search and aim to balance candidate exposure based on protected characteristics. However, ATS in recruitment introduce unique challenges due to their high-stakes nature and the decision-making context in which they operate. In this paper, we present a series of user studies that explore the disconnect between fair exposure and fair outcomes in candidate shortlisting. We focus on how factors such as task design (e.g., how recruiters interact with candidate lists), individual representations of candidates (e.g., national origin cues), and ranking order influence both position bias and demographic balance. Our findings show that while demographic balance may be achieved in terms of ranking visibility, this does not necessarily translate to fair outcomes in terms of who gets shortlisted. Through a crowdsourced experiment and in-depth interviews with recruiters, we identify key task-level, individual, and ranking factors that mediate these effects. We conclude that fairness in ATS rankings is contingent not only on algorithmic design but also on the shortlisting tasks they support, as well as the interfaces, strategies, and assumptions that recruiters use when interacting with candidate lists. Based on these insights, we provide implications for the design of algorithms, interfaces, and recruitment processes that support fairer and more equitable recruitment outcomes.

Traditional ranking algorithms are designed to retrieve the most relevant items for a user’s query, but they often inherit biases from data that can unfairly disadvantage vulnerable groups. Fairness in information access systems (IAS) is typically assessed by comparing the distribution of groups in a ranking to a target distribution, such as the overall group distribution in the dataset. These fairness metrics depend on knowing the true group labels for each item. However, when groups are defined by demographic or sensitive attributes, these labels are often unknown, leading to a setting known as “fairness under unawareness.” To address this, group membership can be inferred using machine-learned classifiers, and group prevalence is estimated by counting the predicted labels. Unfortunately, such an estimation is known to be unreliable under dataset shift, compromising the accuracy of fairness evaluations. In this paper, we introduce a robust fairness estimator based on quantification that effectively handles multiple sensitive attributes beyond binary classifications. Our method outperforms existing baselines across various sensitive attributes and, to the best of our knowledge, is the first to establish a reliable protocol for measuring fairness under unawareness across multiple queries and groups.

Despite the critical importance of the medical domain in Deep Learning, most of the research in this area solely focuses on training models in static environments. It is only in recent years that research has begun to address dynamic environments and tackle the Catastrophic Forgetting problem through Continual Learning (CL) techniques. Previous studies have primarily focused on scenarios such as Domain Incremental Learning and Class Incremental Learning, which do not fully capture the complexity of real-world applications. Therefore, in this work, we propose a novel benchmark combining the challenges of new class arrivals and domain shifts in a single framework, by considering the New Instances and New Classes (NIC) scenario. This benchmark aims to model a realistic CL setting for the multi-label classification problem in medical imaging. Additionally, it encompasses a greater number of tasks compared to previously tested scenarios. Specifically, our benchmark consists of two datasets (NIH and CXP), nineteen classes, and seven tasks. To solve common challenges (e.g., the task inference problem) found in the CIL and NIC scenarios, we propose a novel approach called Replay Consolidation with Label Propagation (RCLP). Our method surpasses existing approaches, exhibiting superior performance with minimal forgetting.

Undesirable biases encoded in the data are key drivers of algorithmic discrimination. Their importance is widely recognized in the algorithmic fairness literature, as well as legislation and standards on anti-discrimination in AI. Despite this recognition, data biases remain understudied, hindering the development of computational best practices for their detection and mitigation. In this work, we present three common data biases and study their individual and joint effect on algorithmic discrimination across a variety of datasets, models, and fairness measures. We find that underrepresentation of vulnerable populations in training sets is less conducive to discrimination than conventionally affirmed, while combinations of proxies and label bias can be far more critical. Consequently, we develop dedicated mechanisms to detect specific types of bias, and combine them into a preliminary construct we refer to as the Data Bias Profile (DBP) . This initial formulation serves as a proof of concept for how different bias signals can be systematically documented. Through a case study with popular fairness datasets, we demonstrate the effectiveness of the DBP in predicting the risk of discriminatory outcomes and the utility of fairness-enhancing interventions. Overall, this article bridges algorithmic fairness research and anti-discrimination policy through a data-centric lens.

Employers are adopting algorithmic hiring technology throughout the recruitment pipeline. Algorithmic fairness is especially applicable in this domain due to its high stakes and structural inequalities. Unfortunately, most work in this space provides partial treatment, often constrained by two competing narratives, optimistically focused on replacing biased recruiter decisions or pessimistically pointing to the automation of discrimination. Whether, and more importantly what types of , algorithmic hiring can be less biased and more beneficial to society than low-tech alternatives currently remains unanswered, to the detriment of trustworthiness. This multidisciplinary survey caters to practitioners and researchers with a balanced and integrated coverage of systems, biases, measures, mitigation strategies, datasets, and legal aspects of algorithmic hiring and fairness. Our work supports a contextualized understanding and governance of this technology by highlighting current opportunities and limitations, providing recommendations for future work to ensure shared benefits for all stakeholders.

Fairness and equity have become central to ranking problems in information access systems, such as search engines, recommender systems, or marketplaces. To date, several types of fair ranking measures have been proposed, including diversity, exposure, and pairwise fairness measures. Out of those, pairwise fairness is a family of metrics whose normative grounding has not been clearly explicated, leading to uncertainty with respect to the construct that is being measured and how it relates to stakeholders' desiderata.

Algorithms and models are increasingly deployed to inform decisions about people, inevitably affecting their lives. As a consequence, those in charge of developing these models must carefully evaluate their impact on different groups of people and favour group fairness, that is, ensure that groups determined by sensitive demographic attributes, such as race or sex, are not treated unjustly. To achieve this goal, the availability (awareness) of these demographic attributes to those evaluating the impact of these models is fundamental. Unfortunately, collecting and storing these attributes is often in conflict with industry practices and legislation on data minimisation and privacy. For this reason, it can be hard to measure the group fairness of trained models, even from within the companies developing them. In this work, we tackle the problem of measuring group fairness under unawareness of sensitive attributes, by using techniques from quantification, a supervised learning task concerned with directly providing group-level prevalence estimates (rather than individual-level class labels). We show that quantification approaches are particularly suited to tackle the fairness-under-unawareness problem, as they are robust to inevitable distribution shifts while at the same time decoupling the (desirable) objective of measuring group fairness from the (undesirable) side effect of allowing the inference of sensitive attributes of individuals. More in detail, we show that fairness under unawareness can be cast as a quantification problem and solved with proven methods from the quantification literature. We show that these methods outperform previous approaches to measure demographic parity in five experimental protocols, corresponding to important challenges that complicate the estimation of classifier fairness under unawareness.

Abstract Data-driven algorithms are studied and deployed in diverse domains to support critical decisions, directly impacting people’s well-being. As a result, a growing community of researchers has been investigating the equity of existing algorithms and proposing novel ones, advancing the understanding of risks and opportunities of automated decision-making for historically disadvantaged populations. Progress in fair machine learning and equitable algorithm design hinges on data, which can be appropriately used only if adequately documented. Unfortunately, the algorithmic fairness community, as a whole, suffers from a collective data documentation debt caused by a lack of information on specific resources (opacity) and scatteredness of available information (sparsity). In this work, we target this data documentation debt by surveying over two hundred datasets employed in algorithmic fairness research, and producing standardized and searchable documentation for each of them. Moreover we rigorously identify the three most popular fairness datasets, namely Adult, COMPAS, and German Credit, for which we compile in-depth documentation. This unifying documentation effort supports multiple contributions. Firstly, we summarize the merits and limitations of Adult, COMPAS, and German Credit, adding to and unifying recent scholarship, calling into question their suitability as general-purpose fairness benchmarks. Secondly, we document hundreds of available alternatives, annotating their domain and supported fairness tasks, along with additional properties of interest for fairness practitioners and researchers, including their format, cardinality, and the sensitive attributes they encode. We summarize this information, zooming in on the tasks, domains, and roles of these resources. Finally, we analyze these datasets from the perspective of five important data curation topics: anonymization, consent, inclusivity, labeling of sensitive attributes, and transparency. We discuss different approaches and levels of attention to these topics, making them tangible, and distill them into a set of best practices for the curation of novel resources.

We conduct an audit of pricing algorithms employed by companies in the Italian car insurance industry, primarily by gathering quotes through a popular comparison website. While acknowledging the complexity of the industry, we find evidence of several problematic practices. We show that birthplace and gender have a direct and sizeable impact on the prices quoted to drivers, despite national and international regulations against their use. Birthplace, in particular, is used quite frequently to the disadvantage of foreign-born drivers and drivers born in certain Italian cities. In extreme cases, a driver born in Laos may be charged 1,000 more than a driver born in Milan, all else being equal. For a subset of our sample, we collect quotes directly on a company website, where the direct influence of gender and birthplace is confirmed. Finally, we find that drivers with riskier profiles tend to see fewer quotes in the aggregator result pages, substantiating concerns of differential treatment raised in the past by Italian insurance regulators.

Component Analysis (CA) comprises of statistical techniques that decompose signals into appropriate latent components, relevant to a task-at-hand (e.g., clustering, segmentation, classification). Recently, an explosion of research in CA has been witnessed, with several novel probabilistic models proposed (e.g., Probabilistic Principal CA, Probabilistic Linear Discriminant Analysis (PLDA), Probabilistic Canonical Correlation Analysis). PLDA is a popular generative probabilistic CA method, that incorporates knowledge regarding class-labels and furthermore introduces class-specific and sample-specific latent spaces. While PLDA has been shown to outperform several state-of-the-art methods, it is nevertheless a static model; any feature-level temporal dependencies that arise in the data are ignored. As has been repeatedly shown, appropriate modelling of temporal dynamics is crucial for the analysis of temporal data (e.g., videos). In this light, we propose the first, to the best of our knowledge, probabilistic LDA formulation that models dynamics, the so-called Dynamic-PLDA (DPLDA). DPLDA is a generative model suitable for video classification and is able to jointly model the label information (e.g., face identity, consistent over videos of the same subject), as well as dynamic variations of each individual video. Experiments on video classification tasks such as face and facial expression recognition show the efficacy of the proposed method.