Research Papers

How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning

Lingjuan Lyu, Yitong Li, Karthik Nandakumar +2

This paper firstly considers the research problem of fairness in collaborative deep learning, while ensuring privacy. A novel reputation system is proposed through digital tokens and local credibility to ensure fairness, in combination with differential privacy to guarantee privacy. In particular, we build a fair and differentially private decentralised deep learning framework called FDPDDL, which enables parties to derive more accurate local models in a fair and private manner by using our developed two-stage scheme: during the initialisation stage, artificial samples generated by Differentially Private Generative Adversarial Network (DPGAN) are used to mutually benchmark the local credibility of each party and generate initial tokens; during the update stage, Differentially Private SGD (DPSGD) is used to facilitate collaborative privacy-preserving deep learning, and local credibility and tokens of each party are updated according to the quality and quantity of individually released gradients. Experimental results on benchmark datasets under three realistic settings demonstrate that FDPDDL achieves high fairness, yields comparable accuracy to the centralised and distributed frameworks, and delivers better accuracy than the standalone framework.

In this paper, we cast fair machine learning as invariant machine learning. We first formulate a version of individual fairness that enforces invariance on certain sensitive sets. We then design a transport-based regularizer that enforces this version of individual fairness and develop an algorithm to minimize the regularizer efficiently. Our theoretical results guarantee the proposed approach trains certifiably fair ML models. Finally, in the experimental studies we demonstrate improved fairness metrics in comparison to several recent fair training procedures on three ML tasks that are susceptible to algorithmic bias.

Advances in computing power, deep learning architectures, and expert labelled datasets have spurred the development of medical imaging artificial intelligence systems that rival clinical experts in a variety of scenarios. The National Institutes of Health in 2018 identified key focus areas for the future of artificial intelligence in medical imaging, creating a foundational roadmap for research in image acquisition, algorithms, data standardization, and translatable clinical decision support systems. Among the key issues raised in the report: data availability, need for novel computing architectures and explainable AI algorithms, are still relevant despite the tremendous progress made over the past few years alone. Furthermore, translational goals of data sharing, validation of performance for regulatory approval, generalizability and mitigation of unintended bias must be accounted for early in the development process. In this perspective paper we explore challenges unique to high dimensional clinical imaging data, in addition to highlighting some of the technical and ethical considerations in developing high-dimensional, multi-modality, machine learning systems for clinical decision support.

The growing importance of understanding and addressing algorithmic bias in artificial intelligence (AI) has led to a surge in research on AI fairness, which often assumes that the underlying data is independent and identically distributed (IID). However, real-world data frequently exists in non-IID graph structures that capture connections among individual units. To effectively mitigate bias in AI systems, it is essential to bridge the gap between traditional fairness literature, designed for IID data, and the prevalence of non-IID graph data. This survey reviews recent advancements in fairness amidst non-IID graph data, including the newly introduced fair graph generation and the commonly studied fair graph classification. In addition, available datasets and evaluation metrics for future research are identified, the limitations of existing work are highlighted, and promising future directions are proposed.

The increasing deployment of artificial intelligence (AI) tools to inform decision making across diverse areas including healthcare, employment, social benefits, and government policy, presents a serious risk for disabled people, who have been shown to face bias in AI implementations. While there has been significant work on analysing and mitigating algorithmic bias, the broader mechanisms of how bias emerges in AI applications are not well understood, hampering efforts to address bias where it begins. In this article, we illustrate how bias in AI-assisted decision making can arise from a range of specific design decisions, each of which may seem self-contained and non-biasing when considered separately. These design decisions include basic problem formulation, the data chosen for analysis, the use the AI technology is put to, and operational design elements in addition to the core algorithmic design. We draw on three historical models of disability common to different decision-making settings to demonstrate how differences in the definition of disability can lead to highly distinct decisions on each of these aspects of design, leading in turn to AI technologies with a variety of biases and downstream effects. We further show that the potential harms arising from inappropriate definitions of disability in fundamental design stages are further amplified by a lack of transparency and disabled participation throughout the AI design process. Our analysis provides a framework for critically examining AI technologies in decision-making contexts and guiding the development of a design praxis for disability-related AI analytics. We put forth this article to provide key questions to facilitate disability-led design and participatory development to produce more fair and equitable AI technologies in disability-related contexts.

Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models

Esma Balkir, Svetlana Kiritchenko, Isar Nejadgholi +1

Motivations for methods in explainable artificial intelligence (XAI) often include detecting, quantifying and mitigating bias, and contributing to making machine learning models fairer. However, exactly how an XAI method can help in combating biases is often left unspecified. In this paper, we briefly review trends in explainability and fairness in NLP research, identify the current practices in which explainability methods are applied to detect and mitigate bias, and investigate the barriers preventing XAI methods from being used more widely in tackling fairness issues.

There has been a surge of recent interest in sociocultural diversity in machine learning (ML) research, with researchers (i) examining the benefits of diversity as an organizational solution for alleviating problems with algorithmic bias, and (ii) proposing measures and methods for implementing diversity as a design desideratum in the construction of predictive algorithms. Currently, however, there is a gap between discussions of measures and benefits of diversity in ML, on the one hand, and the broader research on the underlying concepts of diversity and the precise mechanisms of its functional benefits, on the other. This gap is problematic because diversity is not a monolithic concept. Rather, different concepts of diversity are based on distinct rationales that should inform how we measure diversity in a given context. Similarly, the lack of specificity about the precise mechanisms underpinning diversity's potential benefits can result in uninformative generalities, invalid experimental designs, and illicit interpretations of findings. In this work, we draw on research in philosophy, psychology, and social and organizational sciences to make three contributions: First, we introduce a taxonomy of different diversity concepts from philosophy of science, and explicate the distinct epistemic and political rationales underlying these concepts. Second, we provide an overview of mechanisms by which diversity can benefit group performance. Third, we situate these taxonomies--of concepts and mechanisms--in the lifecycle of sociotechnical ML systems and make a case for their usefulness in fair and accountable ML. We do so by illustrating how they clarify the discourse around diversity in the context of ML systems, promote the formulation of more precise research questions about diversity's impact, and provide conceptual tools to further advance research and practice.

On the Validity of Arrest as a Proxy for Offense: Race and the Likelihood of Arrest for Violent Crimes

Riccardo Fogliato, Alice Xiang, Zachary Lipton +2

The risk of re-offense is considered in decision-making at many stages of the criminal justice system, from pre-trial, to sentencing, to parole. To aid decision makers in their assessments, institutions increasingly rely on algorithmic risk assessment instruments (RAIs). These tools assess the likelihood that an individual will be arrested for a new criminal offense within some time window following their release. However, since not all crimes result in arrest, RAIs do not directly assess the risk of re-offense. Furthermore, disparities in the likelihood of arrest can potentially lead to biases in the resulting risk scores. Several recent validations of RAIs have therefore focused on arrests for violent offenses, which are viewed as being more accurate reflections of offending behavior. In this paper, we investigate biases in violent arrest data by analysing racial disparities in the likelihood of arrest for White and Black violent offenders. We focus our study on 2007--2016 incident-level data of violent offenses from 16 US states as recorded in the National Incident Based Reporting System (NIBRS). Our analysis shows that the magnitude and direction of the racial disparities depend on various characteristics of the crimes. In addition, our investigation reveals large variations in arrest rates across geographical locations and offense types. We discuss the implications of the observed disconnect between re-arrest and re-offense in the context of RAIs and the challenges around the use of data from NIBRS to correct for the sampling bias.

Understanding the Representation and Representativeness of Age in AI Data Sets

Joon Sung Park, Michael S. Bernstein, Robin N. Brewer +2

A diverse representation of different demographic groups in AI training data sets is important in ensuring that the models will work for a large range of users. To this end, recent efforts in AI fairness and inclusion have advocated for creating AI data sets that are well-balanced across race, gender, socioeconomic status, and disability status. In this paper, we contribute to this line of work by focusing on the representation of age by asking whether older adults are represented proportionally to the population at large in AI data sets. We examine publicly-available information about 92 face data sets to understand how they codify age as a case study to investigate how the subjects' ages are recorded and whether older generations are represented. We find that older adults are very under-represented; five data sets in the study that explicitly documented the closed age intervals of their subjects included older adults (defined as older than 65 years), while only one included oldest-old adults (defined as older than 85 years). Additionally, we find that only 24 of the data sets include any age-related information in their documentation or metadata, and that there is no consistent method followed across these data sets to collect and record the subjects' ages. We recognize the unique difficulties in creating representative data sets in terms of age, but raise it as an important dimension that researchers and engineers interested in inclusive AI should consider.

Individuals of modern societies share ideas and participate in collective processes within a pervasive, variable, and mostly hidden ecosystem of content filtering technologies that determine what information we see online. Despite the impact of these algorithms on daily life and society, little is known about their effect on information transfer and opinion formation. It is thus unclear to what extent algorithmic bias has a harmful influence on collective decision-making, such as a tendency to polarize debate. Here we introduce a general theoretical framework to systematically link models of opinion dynamics, social network structure, and content filtering. We showcase the flexibility of our framework by exploring a family of binary-state opinion dynamics models where information exchange lies in a spectrum from pairwise to group interactions. All models show an opinion polarization regime driven by algorithmic bias and modular network structure. The role of content filtering is, however, surprisingly nuanced; for pairwise interactions it leads to polarization, while for group interactions it promotes coexistence of opinions. This allows us to pinpoint which social interactions are robust against algorithmic bias, and which ones are susceptible to bias-enhanced opinion polarization. Our framework gives theoretical ground for the development of heuristics to tackle harmful effects of online bias, such as information bottlenecks, echo chambers, and opinion radicalization.

Many ML models are opaque to humans, producing decisions too complex for humans to easily understand. In response, explainable artificial intelligence (XAI) tools that analyze the inner workings of a model have been created. Despite these tools' strength in translating model behavior, critiques have raised concerns about the impact of XAI tools as a tool for `fairwashing` by misleading users into trusting biased or incorrect models. In this paper, we created a framework for evaluating explainable AI tools with respect to their capabilities for detecting and addressing issues of bias and fairness as well as their capacity to communicate these results to their users clearly. We found that despite their capabilities in simplifying and explaining model behavior, many prominent XAI tools lack features that could be critical in detecting bias. Developers can use our framework to suggest modifications needed in their toolkits to reduce issues likes fairwashing.

Activists, journalists, and scholars have long raised critical questions about the relationship between diversity, representation, and structural exclusions in data-intensive tools and services. We build on work mapping the emergent landscape of corporate AI ethics to center one outcome of these conversations: the incorporation of diversity and inclusion in corporate AI ethics activities. Using interpretive document analysis and analytic tools from the values in design field, we examine how diversity and inclusion work is articulated in public-facing AI ethics documentation produced by three companies that create application and services layer AI infrastructure: Google, Microsoft, and Salesforce. We find that as these documents make diversity and inclusion more tractable to engineers and technical clients, they reveal a drift away from civil rights justifications that resonates with the managerialization of diversity by corporations in the mid-1980s. The focus on technical artifacts, such as diverse and inclusive datasets, and the replacement of equity with fairness make ethical work more actionable for everyday practitioners. Yet, they appear divorced from broader DEI initiatives and other subject matter experts that could provide needed context to nuanced decisions around how to operationalize these values. Finally, diversity and inclusion, as configured by engineering logic, positions firms not as ethics owners but as ethics allocators; while these companies claim expertise on AI ethics, the responsibility of defining who diversity and inclusion are meant to protect and where it is relevant is pushed downstream to their customers.