arXiv subjects

Suresh Venkatasubramanian

Publications and source records attributed to Suresh Venkatasubramanian.

At least 37 records · Page 2Linked to original sources

arXiv2024

Community Driven Approaches to Research in Technology & Society CCC Workshop Report

Based on our workshop activities, we outlined three ways in which research can support community needs: (1) Mapping the ecosystem of both the players and ecosystem and harm landscapes, (2) Counter-Programming, which entails using the same surveillance tools that communities are subjected to observe the entities doing the surveilling, effectively protecting people from surveillance, and conducting ethical data collection to measure the impact of these technologies, and (3) Engaging in positive visions and tools for empowerment so that technology can bring good instead of harm. In order to effectively collaborate on the aforementioned directions, we outlined seven important mechanisms for effective collaboration: (1) Never expect free labor of community members, (2) Ensure goals are aligned between all collaborators, (3) Elevate community members to leadership positions, (4) Understand no group is a monolith, (5) Establish a common language, (6) Discuss organization roles and goals of the project transparently from the start, and (7) Enable a recourse for harm. We recommend that anyone engaging in community-based research (1) starts with community-defined solutions, (2) provides alternatives to digital services/information collecting mechanisms, (3) prohibits harmful automated systems, (4) transparently states any systems impact, (5) minimizes and protects data, (6) proactively demonstrates a system is safe and beneficial prior to deployment, and (7) provides resources directly to community partners. Throughout the recommendation section of the report, we also provide specific recommendations for funding agencies, academic institutions, and individual researchers.

cs.CY↗

arXiv2024

To Pool or Not To Pool: Analyzing the Regularizing Effects of Group-Fair Training on Shared Models

In fair machine learning, one source of performance disparities between groups is over-fitting to groups with relatively few training samples. We derive group-specific bounds on the generalization error of welfare-centric fair machine learning that benefit from the larger sample size of the majority group. We do this by considering group-specific Rademacher averages over a restricted hypothesis class, which contains the family of models likely to perform well with respect to a fair learning objective (e.g., a power-mean). Our simulations demonstrate these bounds improve over a naive method, as expected by theory, with particularly significant improvement for smaller group sizes.

cs.LG↗

arXiv2023

Repairing Regressors for Fair Binary Classification at Any Decision Threshold

We study the problem of post-processing a supervised machine-learned regressor to maximize fair binary classification at all decision thresholds. By decreasing the statistical distance between each group's score distributions, we show that we can increase fair performance across all thresholds at once, and that we can do so without a large decrease in accuracy. To this end, we introduce a formal measure of Distributional Parity, which captures the degree of similarity in the distributions of classifications for different protected groups. Our main result is to put forward a novel post-processing algorithm based on optimal transport, which provably maximizes Distributional Parity, thereby attaining common notions of group fairness like Equalized Odds or Equal Opportunity at all thresholds. We demonstrate on two fairness benchmarks that our technique works well empirically, while also outperforming and generalizing similar techniques from related work.

cs.LG↗

arXiv2023

Information access representations and social capital in networks

Social network position confers power and social capital. In the setting of online social networks that have massive reach, creating mathematical representations of social capital is an important step towards understanding how network position can differentially confer advantage to different groups and how network position can itself be a source of advantage. In this paper, we use well established models for information flow on networks as a base to propose a formal descriptor of the network position of a node as represented by its information access. Combining these descriptors allows a full representation of social capital across the network. Using real-world networks, we demonstrate that this representation allows the identification of differences between groups based on network specific measures of inequality of access.

cs.SI↗

arXiv2023

The Misuse of AUC: What High Impact Risk Assessment Gets Wrong

When determining which machine learning model best performs some high impact risk assessment task, practitioners commonly use the Area under the Curve (AUC) to defend and validate their model choices. In this paper, we argue that the current use and understanding of AUC as a model performance metric misunderstands the way the metric was intended to be used. To this end, we characterize the misuse of AUC and illustrate how this misuse negatively manifests in the real world across several risk assessment domains. We locate this disconnect in the way the original interpretation of AUC has shifted over time to the point where issues pertaining to decision thresholds, class balance, statistical uncertainty, and protected groups remain unaddressed by AUC-based model comparisons, and where model choices that should be the purview of policymakers are hidden behind the veil of mathematical rigor. We conclude that current model validation practices involving AUC are not robust, and often invalid.

cs.CY↗

arXiv2022

Reducing Access Disparities in Networks using Edge Augmentation

In social networks, a node's position is a form of \it{social capital}. Better-positioned members not only benefit from (faster) access to diverse information, but innately have more potential influence on information spread. Structural biases often arise from network formation, and can lead to significant disparities in information access based on position. Further, processes such as link recommendation can exacerbate this inequality by relying on network structure to augment connectivity. We argue that one can understand and quantify this social capital through the lens of information flow in the network. We consider the setting where all nodes may be sources of distinct information, and a node's (dis)advantage deems its ability to access all information available on the network. We introduce three new measures of advantage (broadcast, influence, and control), which are quantified in terms of position in the network using \it{access signatures} -- vectors that represent a node's ability to share information. We then consider the problem of improving equity by making interventions to increase the access of the least-advantaged nodes. We argue that edge augmentation is most appropriate for mitigating bias in the network structure, and frame a budgeted intervention problem for maximizing minimum pairwise access. Finally, we propose heuristic strategies for selecting edge augmentations and empirically evaluate their performance on a corpus of real-world social networks. We demonstrate that a small number of interventions significantly increase the broadcast measure of access for the least-advantaged nodes (over 5 times more than random), and also improve the minimum influence. Additional analysis shows that these interventions can also dramatically shrink the gap in advantage between nodes (over \%82) and reduce disparities between their access signatures.

cs.SI↗

arXiv2022

Measuring and mitigating voting access disparities: a study of race and polling locations in Florida and North Carolina

Voter suppression and associated racial disparities in access to voting are long-standing civil rights concerns in the United States. Barriers to voting have taken many forms over the decades. A history of violent explicit discouragement has shifted to more subtle access limitations that can include long lines and wait times, long travel times to reach a polling station, and other logistical barriers to voting. Our focus in this work is on quantifying disparities in voting access pertaining to the overall time-to-vote, and how they could be remedied via a better choice of polling location or provisioning more sites where voters can cast ballots. However, appropriately calibrating access disparities is difficult because of the need to account for factors such as population density and different community expectations for reasonable travel times. In this paper, we quantify access to polling locations, developing a methodology for the calibrated measurement of racial disparities in polling location "load" and distance to polling locations. We apply this methodology to a study of real-world data from Florida and North Carolina to identify disparities in voting access from the 2020 election. We also introduce algorithms, with modifications to handle scale, that can reduce these disparities by suggesting new polling locations from a given list of identified public locations (including schools and libraries). Applying these algorithms on the 2020 election location data also helps to expose and explore tradeoffs between the cost of allocating more polling locations and the potential impact on access disparities. The developed voting access measurement methodology and algorithmic remediation technique is a first step in better polling location assignment.

cs.CY↗

arXiv2022

It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks

Risk assessment instrument (RAI) datasets, particularly ProPublica's COMPAS dataset, are commonly used in algorithmic fairness papers due to benchmarking practices of comparing algorithms on datasets used in prior work. In many cases, this data is used as a benchmark to demonstrate good performance without accounting for the complexities of criminal justice (CJ) processes. However, we show that pretrial RAI datasets can contain numerous measurement biases and errors, and due to disparities in discretion and deployment, algorithmic fairness applied to RAI datasets is limited in making claims about real-world outcomes. These reasons make the datasets a poor fit for benchmarking under assumptions of ground truth and real-world impact. Furthermore, conventional practices of simply replicating previous data experiments may implicitly inherit or edify normative positions without explicitly interrogating value-laden assumptions. Without context of how interdisciplinary fields have engaged in CJ research and context of how RAIs operate upstream and downstream, algorithmic fairness practices are misaligned for meaningful contribution in the context of CJ, and would benefit from transparent engagement with normative considerations and values related to fairness, justice, and equality. These factors prompt questions about whether benchmarks for intrinsically socio-technical systems like the CJ system can exist in a beneficial and ethical way.

cs.CY↗

arXiv2021

Precarity: Modeling the Long Term Effects of Compounded Decisions on Individual Instability

When it comes to studying the impacts of decision making, the research has been largely focused on examining the fairness of the decisions, the long-term effects of the decision pipelines, and utility-based perspectives considering both the decision-maker and the individuals. However, there has hardly been any focus on precarity which is the term that encapsulates the instability in people's lives. That is, a negative outcome can overspread to other decisions and measures of well-being. Studying precarity necessitates a shift in focus - from the point of view of the decision-maker to the perspective of the decision subject. This centering of the subject is an important direction that unlocks the importance of parting with aggregate measures to examine the long-term effects of decision making. To address this issue, in this paper, we propose a modeling framework that simulates the effects of compounded decision-making on precarity over time. Through our simulations, we are able to show the heterogeneity of precarity by the non-uniform ruinous aftereffects of negative decisions on different income classes of the underlying population and how policy interventions can help mitigate such effects.

cs.AI↗

arXiv2021

Fair clustering via equitable group representations

What does it mean for a clustering to be fair? One popular approach seeks to ensure that each cluster contains groups in (roughly) the same proportion in which they exist in the population. The normative principle at play is balance: any cluster might act as a representative of the data, and thus should reflect its diversity. But clustering also captures a different form of representativeness. A core principle in most clustering problems is that a cluster center should be representative of the cluster it represents, by being "close" to the points associated with it. This is so that we can effectively replace the points by their cluster centers without significant loss in fidelity, and indeed is a common "use case" for clustering. For such a clustering to be fair, the centers should "represent" different groups equally well. We call such a clustering a group-representative clustering. In this paper, we study the structure and computation of group-representative clusterings. We show that this notion naturally parallels the development of fairness notions in classification, with direct analogs of ideas like demographic parity and equal opportunity. We demonstrate how these notions are distinct from and cannot be captured by balance-based notions of fairness. We present approximation algorithms for group representative $k$-median clustering and couple this with an empirical evaluation on various real-world data sets.

cs.LG↗

arXiv2021

A Research Ecosystem for Secure Computing

Computing devices are vital to all areas of modern life and permeate every aspect of our society. The ubiquity of computing and our reliance on it has been accelerated and amplified by the COVID-19 pandemic. From education to work environments to healthcare to defense to entertainment - it is hard to imagine a segment of modern life that is not touched by computing. The security of computers, systems, and applications has been an active area of research in computer science for decades. However, with the confluence of both the scale of interconnected systems and increased adoption of artificial intelligence, there are many research challenges the community must face so that our society can continue to benefit and risks are minimized, not multiplied. Those challenges range from security and trust of the information ecosystem to adversarial artificial intelligence and machine learning. Along with basic research challenges, more often than not, securing a system happens after the design or even deployment, meaning the security community is routinely playing catch-up and attempting to patch vulnerabilities that could be exploited any minute. While security measures such as encryption and authentication have been widely adopted, questions of security tend to be secondary to application capability. There needs to be a sea-change in the way we approach this critically important aspect of the problem: new incentives and education are at the core of this change. Now is the time to refocus research community efforts on developing interconnected technologies with security "baked in by design" and creating an ecosystem that ensures adoption of promising research developments. To realize this vision, two additional elements of the ecosystem are necessary - proper incentive structures for adoption and an educated citizenry that is well versed in vulnerabilities and risks.

cs.CY↗

arXiv2020

Interdisciplinary Approaches to Understanding Artificial Intelligence's Impact on Society

Innovations in AI have focused primarily on the questions of "what" and "how"-algorithms for finding patterns in web searches, for instance-without adequate attention to the possible harms (such as privacy, bias, or manipulation) and without adequate consideration of the societal context in which these systems operate. In part, this is driven by incentives and forces in the tech industry, where a more product-driven focus tends to drown out broader reflective concerns about potential harms and misframings. But this focus on what and how is largely a reflection of the engineering and mathematics-focused training in computer science, which emphasizes the building of tools and development of computational concepts. As a result of this tight technical focus, and the rapid, worldwide explosion in its use, AI has come with a storm of unanticipated socio-technical problems, ranging from algorithms that act in racially or gender-biased ways, get caught in feedback loops that perpetuate inequalities, or enable unprecedented behavioral monitoring surveillance that challenges the fundamental values of free, democratic societies. Given that AI is no longer solely the domain of technologists but rather of society as a whole, we need tighter coupling of computer science and those disciplines that study society and societal values.

cs.CY↗

arXiv2020

Evolving Methods for Evaluating and Disseminating Computing Research

Social and technical trends have significantly changed methods for evaluating and disseminating computing research. Traditional venues for reviewing and publishing, such as conferences and journals, worked effectively in the past. Recently, trends have created new opportunities but also put new pressures on the process of review and dissemination. For example, many conferences have seen large increases in the number of submissions. Likewise, dissemination of research ideas has become dramatically through publication venues such as arXiv.org and social media networks. While these trends predate COVID-19, the pandemic could accelerate longer term changes. Based on interviews with leading academics in computing research, our findings include: (1) Trends impacting computing research are largely positive and have increased the participation, scope, accessibility, and speed of the research process. (2) Challenges remain in securing the integrity of the process, including addressing ways to scale the review process, avoiding attempts to misinform or confuse the dissemination of results, and ensuring fairness and broad participation in the process itself. Based on these findings, we recommend: (1) Regularly polling members of the computing research community, including program and general conference chairs, journal editors, authors, reviewers, etc., to identify specific challenges they face to better understand these issues. (2) An influential body, such as the Computing Research Association regularly issues a "State of the Computing Research Enterprise" report to update the community on trends, both positive and negative, impacting the computing research enterprise. (3) A deeper investigation, specifically to better understand the influence that social media and preprint archives have on computing research, is conducted.

cs.CY↗

arXiv2020

Problems with Shapley-value-based explanations as feature importance measures

Game-theoretic formulations of feature importance have become popular as a way to "explain" machine learning models. These methods define a cooperative game between the features of a model and distribute influence among these input elements using some form of the game's unique Shapley values. Justification for these methods rests on two pillars: their desirable mathematical properties, and their applicability to specific motivations for explanations. We show that mathematical problems arise when Shapley values are used for feature importance and that the solutions to mitigate these necessarily induce further complexity, such as the need for causal reasoning. We also draw on additional literature to argue that Shapley values do not provide explanations which suit human-centric goals of explainability.

cs.AI↗

arXiv2019

Equalizing Recourse across Groups

The rise in machine learning-assisted decision-making has led to concerns about the fairness of the decisions and techniques to mitigate problems of discrimination. If a negative decision is made about an individual (denying a loan, rejecting an application for housing, and so on) justice dictates that we be able to ask how we might change circumstances to get a favorable decision the next time. Moreover, the ability to change circumstances (a better education, improved credentials) should not be limited to only those with access to expensive resources. In other words, \emph{recourse} for negative decisions should be considered a desirable value that can be equalized across (demographically defined) groups. This paper describes how to build models that make accurate predictions while still ensuring that the penalties for a negative outcome do not disadvantage different groups disproportionately. We measure recourse as the distance of an individual from the decision boundary of a classifier. We then introduce a regularized objective to minimize the difference in recourse across groups. We explore linear settings and further extend recourse to non-linear settings as well as model-agnostic settings where the exact distance from boundary cannot be calculated. Our results show that we can successfully decrease the unfairness in recourse while maintaining classifier performance.

cs.LG↗

arXiv2019

Disentangling Influence: Using Disentangled Representations to Audit Model Predictions

Motivated by the need to audit complex and black box models, there has been extensive research on quantifying how data features influence model predictions. Feature influence can be direct (a direct influence on model outcomes) and indirect (model outcomes are influenced via proxy features). Feature influence can also be expressed in aggregate over the training or test data or locally with respect to a single point. Current research has typically focused on one of each of these dimensions. In this paper, we develop disentangled influence audits, a procedure to audit the indirect influence of features. Specifically, we show that disentangled representations provide a mechanism to identify proxy features in the dataset, while allowing an explicit computation of feature influence on either individual outcomes or aggregate-level outcomes. We show through both theory and experiments that disentangled influence audits can both detect proxy features and show, for each individual or in aggregate, which of these proxy features affects the classifier being audited the most. In this respect, our method is more powerful than existing methods for ascertaining feature influence.

cs.LG↗

arXiv2019

Gaps in Information Access in Social Networks

The study of influence maximization in social networks has largely ignored disparate effects these algorithms might have on the individuals contained in the social network. Individuals may place a high value on receiving information, e.g. job openings or advertisements for loans. While well-connected individuals at the center of the network are likely to receive the information that is being distributed through the network, poorly connected individuals are systematically less likely to receive the information, producing a gap in access to the information between individuals. In this work, we study how best to spread information in a social network while minimizing this access gap. We propose to use the maximin social welfare function as an objective function, where we maximize the minimum probability of receiving the information under an intervention. We prove that in this setting this welfare function constrains the access gap whereas maximizing the expected number of nodes reached does not. We also investigate the difficulties of using the maximin, and present hardness results and analysis for standard greedy strategies. Finally, we investigate practical ways of optimizing for the maximin, and give empirical evidence that a simple greedy-based strategy works well in practice.

cs.SI↗

arXiv2019

Fairness in representation: quantifying stereotyping as a representational harm

While harms of allocation have been increasingly studied as part of the subfield of algorithmic fairness, harms of representation have received considerably less attention. In this paper, we formalize two notions of stereotyping and show how they manifest in later allocative harms within the machine learning pipeline. We also propose mitigation strategies and demonstrate their effectiveness on synthetic datasets.

cs.LG↗