arXiv subjects

Julia Stoyanovich

Publications and source records attributed to Julia Stoyanovich.

At least 55 records · Page 3Linked to original sources

arXiv2022

Towards Substantive Conceptions of Algorithmic Fairness: Normative Guidance from Equal Opportunity Doctrines

In this work we use Equal Oppportunity (EO) doctrines from political philosophy to make explicit the normative judgements embedded in different conceptions of algorithmic fairness. We contrast formal EO approaches that narrowly focus on fair contests at discrete decision points, with substantive EO doctrines that look at people's fair life chances more holistically over the course of a lifetime. We use this taxonomy to provide a moral interpretation of the impossibility results as the incompatibility between different conceptions of a fair contest -- foward-looking versus backward-looking -- when people do not have fair life chances. We use this result to motivate substantive conceptions of algorithmic fairness and outline two plausible procedures based on the luck-egalitarian doctrine of EO, and Rawls's principle of fair equality of opportunity.

cs.CY↗

arXiv2022

Think About the Stakeholders First! Towards an Algorithmic Transparency Playbook for Regulatory Compliance

Increasingly, laws are being proposed and passed by governments around the world to regulate Artificial Intelligence (AI) systems implemented into the public and private sectors. Many of these regulations address the transparency of AI systems, and related citizen-aware issues like allowing individuals to have the right to an explanation about how an AI system makes a decision that impacts them. Yet, almost all AI governance documents to date have a significant drawback: they have focused on what to do (or what not to do) with respect to making AI systems transparent, but have left the brunt of the work to technologists to figure out how to build transparent systems. We fill this gap by proposing a novel stakeholder-first approach that assists technologists in designing transparent, regulatory compliant systems. We also describe a real-world case-study that illustrates how this approach can be used in practice.

cs.CY↗

arXiv2022

Temporal graph patterns by timed automata

Temporal graphs represent graph evolution over time, and have been receiving considerable research attention. Work on expressing temporal graph patterns or discovering temporal motifs typically assumes relatively simple temporal constraints, such as journeys or, more generally, existential constraints, possibly with finite delays. In this paper we propose to use timed automata to express temporal constraints, leading to a general and powerful notion of temporal basic graph pattern (BGP). The new difficulty is the evaluation of the temporal constraint on a large set of matchings. An important benefit of timed automata is that they support an iterative state assignment, which can be useful for early detection of matches and pruning of non-matches. We introduce algorithms to retrieve all instances of a temporal BGP match in a graph, and present results of an extensive experimental evaluation, demonstrating interesting performance trade-offs. We show that an on-demand algorithm that processes total matchings incrementally over time is preferable when dealing with cyclic patterns on sparse graphs. On acyclic patterns or dense graphs, and when connectivity of partial matchings can be guaranteed, the best performance is achieved by maintaining partial matchings over time and allowing automaton evaluation to be fully incremental.

cs.DB↗

arXiv2022

Spending Privacy Budget Fairly and Wisely

Differentially private (DP) synthetic data generation is a practical method for improving access to data as a means to encourage productive partnerships. One issue inherent to DP is that the "privacy budget" is generally "spent" evenly across features in the data set. This leads to good statistical parity with the real data, but can undervalue the conditional probabilities and marginals that are critical for predictive quality of synthetic data. Further, loss of predictive quality may be non-uniform across the data set, with subsets that correspond to minority groups potentially suffering a higher loss. In this paper, we develop ensemble methods that distribute the privacy budget "wisely" to maximize predictive accuracy of models trained on DP data, and "fairly" to bound potential disparities in accuracy across groups and reduce inequality. Our methods are based on the insights that feature importance can inform how privacy budget is allocated, and, further, that per-group feature importance and fairness-related performance objectives can be incorporated in the allocation. These insights make our methods tunable to social contexts, allowing data owners to produce balanced synthetic data for predictive analysis.

cs.LG↗

arXiv2022

An External Stability Audit Framework to Test the Validity of Personality Prediction in AI Hiring

Automated hiring systems are among the fastest-developing of all high-stakes AI systems. Among these are algorithmic personality tests that use insights from psychometric testing, and promise to surface personality traits indicative of future success based on job seekers' resumes or social media profiles. We interrogate the validity of such systems using stability of the outputs they produce, noting that reliability is a necessary, but not a sufficient, condition for validity. Our approach is to (a) develop a methodology for an external audit of stability of predictions made by algorithmic personality tests, and (b) instantiate this methodology in an audit of two systems, Humantic AI and Crystal. Crucially, rather than challenging or affirming the assumptions made in psychometric testing -- that personality is a meaningful and measurable construct, and that personality traits are indicative of future success on the job -- we frame our methodology around testing the underlying assumptions made by the vendors of the algorithmic personality tests themselves. Our main contribution is the development of a socio-technical framework for auditing the stability of algorithmic systems. This contribution is supplemented with an open-source software library that implements the technical components of the audit, and can be used to conduct similar stability audits of algorithmic systems. We instantiate our framework with the audit of two real-world personality prediction systems, namely Humantic AI and Crystal. The application of our audit framework demonstrates that both these systems show substantial instability with respect to key facets of measurement, and hence cannot be considered valid testing instruments.

cs.CY↗

arXiv2022

Temporal Regular Path Queries

In the last decade, substantial progress has been made towards standardizing the syntax of graph query languages, and towards understanding their semantics and complexity of evaluation. In this paper, we consider temporal property graphs (TPGs) and propose temporal regular path queries (TRPQs) that incorporate time into TPG navigation. Starting with design principles, we propose a natural syntactic extension of the MATCH clause of popular graph query languages. We then formally present the semantics of TRPQs, and study the complexity of their evaluation. We show that TRPQs can be evaluated in polynomial time if TPGs are time-stamped with time points, and identify fragments of the TRPQ language that admit efficient evaluation over a more succinct interval-annotated representation. Finally, we implement a fragment of the language in a state-of-the-art dataflow framework, and experimentally demonstrate that TRPQ can be evaluated efficiently.

cs.DB↗

arXiv2021

Fairness as Equality of Opportunity: Normative Guidance from Political Philosophy

Recent interest in codifying fairness in Automated Decision Systems (ADS) has resulted in a wide range of formulations of what it means for an algorithmic system to be fair. Most of these propositions are inspired by, but inadequately grounded in, political philosophy scholarship. This paper aims to correct that deficit. We introduce a taxonomy of fairness ideals using doctrines of Equality of Opportunity (EOP) from political philosophy, clarifying their conceptions in philosophy and the proposed codification in fair machine learning. We arrange these fairness ideals onto an EOP spectrum, which serves as a useful frame to guide the design of a fair ADS in a given context. We use our fairness-as-EOP framework to re-interpret the impossibility results from a philosophical perspective, as the in-compatibility between different value systems, and demonstrate the utility of the framework with several real-world and hypothetical examples. Through our EOP-framework we hope to answer what it means for an ADS to be fair from a moral and political philosophy standpoint, and to pave the way for similar scholarship from ethics and legal experts.

cs.CY↗

arXiv2020

Causal intersectionality for fair ranking

In this paper we propose a causal modeling approach to intersectional fairness, and a flexible, task-specific method for computing intersectionally fair rankings. Rankings are used in many contexts, ranging from Web search results to college admissions, but causal inference for fair rankings has received limited attention. Additionally, the growing literature on causal fairness has directed little attention to intersectionality. By bringing these issues together in a formal causal framework we make the application of intersectionality in fair machine learning explicit, connected to important real world effects and domain knowledge, and transparent about technical limitations. We experimentally evaluate our approach on real and synthetic datasets, exploring its behaviour under different structural assumptions.

cs.LG↗

arXiv2020

Algorithmic Techniques for Necessary and Possible Winners

We investigate the practical aspects of computing the necessary and possible winners in elections over incomplete voter preferences. In the case of the necessary winners, we show how to implement and accelerate the polynomial-time algorithm of Xia and Conitzer. In the case of the possible winners, where the problem is NP-hard, we give a natural reduction to Integer Linear Programming (ILP) for all positional scoring rules and implement it in a leading commercial optimization solver. Further, we devise optimization techniques to minimize the number of ILP executions and, oftentimes, avoid them altogether. We conduct a thorough experimental study that includes the construction of a rich benchmark of election data based on real and synthetic data. Our findings suggest that, the worst-case intractability of the possible winners notwithstanding, the algorithmic techniques presented here scale well and can be used to compute the possible winners in realistic scenarios.

cs.GT↗

arXiv2020

Supporting Hard Queries over Probabilistic Preferences

Preference analysis is widely applied in various domains such as social choice and e-commerce. A recently proposed framework augments the relational database with a preference relation that represents uncertain preferences in the form of statistical ranking models, and provides methods to evaluate Conjunctive Queries (CQs) that express preferences among item attributes. In this paper, we explore the evaluation of queries that are more general and harder to compute. The main focus of this paper is on a class of CQs that cannot be evaluated by previous work. These queries are provably hard since relate variables that represent items being compared. To overcome this hardness, we instantiate these variables with their domain values, rewrite hard CQs as unions of such instantiated queries, and develop several exact and approximate solvers to evaluate these unions of queries. We demonstrate that exact solvers that target specific common kinds of queries are far more efficient than general solvers. Further, we demonstrate that sophisticated approximate solvers making use of importance sampling can be orders of magnitude more efficient than exact solvers, while showing good accuracy. In addition to supporting provably hard CQs, we also present methods to evaluate an important family of count queries, and of top-k queries.

cs.DB↗

arXiv2019

Teaching Responsible Data Science: Charting New Pedagogical Territory

Although numerous ethics courses are available, with many focusing specifically on technology and computer ethics, pedagogical approaches employed in these courses rely exclusively on texts rather than on software development or data analysis. Technical students often consider these courses unimportant and a distraction from the "real" material. To develop instructional materials and methodologies that are thoughtful and engaging, we must strive for balance: between texts and coding, between critique and solution, and between cutting-edge research and practical applicability. Finding such balance is particularly difficult in the nascent field of responsible data science (RDS), where we are only starting to understand how to interface between the intrinsically different methodologies of engineering and social sciences. In this paper we recount a recent experience in developing and teaching an RDS course to graduate and advanced undergraduate students in data science. We then dive into an area that is critically important to RDS -- transparency and interpretability of machine-assisted decision-making, and tie this area to the needs of emerging RDS curricula. Recounting our own experience, and leveraging literature on pedagogical methods in data science and beyond, we propose the notion of an "object-to-interpret-with". We link this notion to "nutritional labels" -- a family of interpretability tools that are gaining popularity in RDS research and practice. With this work we aim to contribute to the nascent area of RDS education, and to inspire others in the community to come together to develop a deeper theoretical understanding of the pedagogical needs of RDS, and contribute concrete educational materials and methodologies that others can use. All course materials are publicly available at https://dataresponsibly.github.io/courses.

cs.CY↗

arXiv2019

FairPrep: Promoting Data to a First-Class Citizen in Studies on Fairness-Enhancing Interventions

The importance of incorporating ethics and legal compliance into machine-assisted decision-making is broadly recognized. Further, several lines of recent work have argued that critical opportunities for improving data quality and representativeness, controlling for bias, and allowing humans to oversee and impact computational processes are missed if we do not consider the lifecycle stages upstream from model training and deployment. Yet, very little has been done to date to provide system-level support to data scientists who wish to develop and deploy responsible machine learning methods. We aim to fill this gap and present FairPrep, a design and evaluation framework for fairness-enhancing interventions. FairPrep is based on a developer-centered design, and helps data scientists follow best practices in software engineering and machine learning. As part of our contribution, we identify shortcomings in existing empirical studies for analyzing fairness-enhancing interventions. We then show how FairPrep can be used to measure the impact of sound best practices, such as hyperparameter tuning and feature scaling. In particular, our results suggest that the high variability of the outcomes of fairness-enhancing interventions observed in previous studies is often an artifact of a lack of hyperparameter tuning. Further, we show that the choice of a data cleaning method can impact the effectiveness of fairness-enhancing interventions.

cs.LG↗

arXiv2019

Balanced Ranking with Diversity Constraints

Many set selection and ranking algorithms have recently been enhanced with diversity constraints that aim to explicitly increase representation of historically disadvantaged populations, or to improve the overall representativeness of the selected set. An unintended consequence of these constraints, however, is reduced in-group fairness: the selected candidates from a given group may not be the best ones, and this unfairness may not be well-balanced across groups. In this paper we study this phenomenon using datasets that comprise multiple sensitive attributes. We then introduce additional constraints, aimed at balancing the \in-group fairness across groups, and formalize the induced optimization problems as integer linear programs. Using these programs, we conduct an experimental evaluation with real datasets, and quantify the feasible trade-offs between balance and overall performance in the presence of diversity constraints.

cs.AI↗

arXiv2019

Transparency, Fairness, Data Protection, Neutrality: Data Management Challenges in the Face of New Regulation

The data revolution continues to transform every sector of science, industry and government. Due to the incredible impact of data-driven technology on society, we are becoming increasingly aware of the imperative to use data and algorithms responsibly -- in accordance with laws and ethical norms. In this article we discuss three recent regulatory frameworks: the European Union's General Data Protection Regulation (GDPR), the New York City Automated Decisions Systems (ADS) Law, and the Net Neutrality principle, that aim to protect the rights of individuals who are impacted by data collection and analysis. These frameworks are prominent examples of a global trend: Governments are starting to recognize the need to regulate data-driven algorithmic technology. Our goal in this paper is to bring these regulatory frameworks to the attention of the data management community, and to underscore the technical challenges they raise and which we, as a community, are well-equipped to address. The main take-away of this article is that legal and ethical norms cannot be incorporated into data-driven systems as an afterthought. Rather, we must think in terms of responsibility by design, viewing it as a systems requirement.

cs.DB↗

arXiv2019

MobilityMirror: Bias-Adjusted Transportation Datasets

We describe customized synthetic datasets for publishing mobility data. Private companies are providing new transportation modalities, and their data is of high value for integrative transportation research, policy enforcement, and public accountability. However, these companies are disincentivized from sharing data not only to protect the privacy of individuals (drivers and/or passengers), but also to protect their own competitive advantage. Moreover, demographic biases arising from how the services are delivered may be amplified if released data is used in other contexts. We describe a model and algorithm for releasing origin-destination histograms that removes selected biases in the data using causality-based methods. We compute the origin-destination histogram of the original dataset then adjust the counts to remove undesirable causal relationships that can lead to discrimination or violate contractual obligations with data owners. We evaluate the utility of the algorithm on real data from a dockless bike share program in Seattle and taxi data in New York, and show that these adjusted transportation datasets can retain utility while removing bias in the underlying data.

cs.DB↗

arXiv2018

On Obtaining Stable Rankings

Decision making is challenging when there is more than one criterion to consider. In such cases, it is common to assign a goodness score to each item as a weighted sum of its attribute values and rank them accordingly. Clearly, the ranking obtained depends on the weights used for this summation. Ideally, one would want the ranked order not to change if the weights are changed slightly. We call this property {\em stability} of the ranking. A consumer of a ranked list may trust the ranking more if it has high stability. A producer of a ranked list prefers to choose weights that result in a stable ranking, both to earn the trust of potential consumers and because a stable ranking is intrinsically likely to be more meaningful. In this paper, we develop a framework that can be used to assess the stability of a provided ranking and to obtain a stable ranking within an "acceptable" range of weight values (called "the region of interest"). We address the case where the user cares about the rank order of the entire set of items, and also the case where the user cares only about the top-$k$ items. Using a geometric interpretation, we propose algorithms that produce stable rankings. In addition to theoretical analyses, we conduct extensive experiments on real datasets that validate our proposal.

cs.DB↗

arXiv2018

Computational Social Choice Meets Databases

We develop a novel framework that aims to create bridges between the computational social choice and the database management communities. This framework enriches the tasks currently supported in computational social choice with relational database context, thus making it possible to formulate sophisticated queries about voting rules, candidates, voters, issues, and positions. At the conceptual level, we give rigorous semantics to queries in this framework by introducing the notions of necessary answers and possible answers to queries. At the technical level, we embark on an investigation of the computational complexity of the necessary answers. We establish a number of results about the complexity of the necessary answers of conjunctive queries involving positional scoring rules that contrast sharply with earlier results about the complexity of the necessary winners.

cs.DB↗

arXiv2018

A Nutritional Label for Rankings

Algorithmic decisions often result in scoring and ranking individuals to determine credit worthiness, qualifications for college admissions and employment, and compatibility as dating partners. While automatic and seemingly objective, ranking algorithms can discriminate against individuals and protected groups, and exhibit low diversity. Furthermore, ranked results are often unstable --- small changes in the input data or in the ranking methodology may lead to drastic changes in the output, making the result uninformative and easy to manipulate. Similar concerns apply in cases where items other than individuals are ranked, including colleges, academic departments, or products. In this demonstration we present Ranking Facts, a Web-based application that generates a "nutritional label" for rankings. Ranking Facts is made up of a collection of visual widgets that implement our latest research results on fairness, stability, and transparency for rankings, and that communicate details of the ranking methodology, or of the output, to the end user. We will showcase Ranking Facts on real datasets from different domains, including college rankings, criminal risk assessment, and financial services.

cs.CY↗