No abstract available.
Model Reconstruction from Model Explanations
We show through theory and experiment that gradient-based explanations of a model quickly reveal the model itself. Our results speak to a tension between the desire to keep a proprietary model secret and the ability to offer model explanations.
On the ...
Actionable Recourse in Linear Classification
Classification models are often used to make decisions that affect humans: whether to approve a loan application, extend a job offer, or provide insurance. In such applications, individuals should have the ability to change the decision of the model. ...
Efficient Search for Diverse Coherent Explanations
This paper proposes new search algorithms for counterfactual explanations based upon mixed integer programming. We are concerned with complex data in which variables may take any value from a contiguous range or an additional set of discrete states. We ...
On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection
Humans are the final decision makers in critical tasks that involve ethical and legal concerns, ranging from recidivism prediction, to medical diagnosis, to fighting against fake news. Although machine learning models can sometimes achieve impressive ...
Problem Formulation and Fairness
Formulating data science problems is an uncertain and difficult process. It requires various forms of discretionary work to translate high-level objectives or strategic goals into tractable problems, necessitating, among other things, the identification ...
50 Years of Test (Un)fairness: Lessons for Machine Learning
Quantitative definitions of what is unfair and what is fair have been introduced in multiple disciplines for well over 50 years, including in education, hiring, and machine learning. We trace how the notion of fairness has been defined within the ...
Fairness and Abstraction in Sociotechnical Systems
A key goal of the fair-ML community is to develop machine-learning based systems that, once introduced into a social context, can achieve social and legal outcomes such as fairness, justice, and due process. Bedrock concepts in computer science---such ...
Clear Sanctions, Vague Rewards: How China's Social Credit System Currently Defines "Good" and "Bad" Behavior
China's Social Credit System (SCS, 社会信用体系 or shehui xinyong tixi) is expected to become the first digitally-implemented nationwide scoring system with the purpose to rate the behavior of citizens, companies, and other entities. Thereby, in the SCS, "...
A Taxonomy of Ethical Tensions in Inferring Mental Health States from Social Media
Powered by machine learning techniques, social media provides an unobtrusive lens into individual behaviors, emotions, and psychological states. Recent research has successfully employed social media data to predict mental health states of individuals, ...
Dissecting Racial Bias in an Algorithm that Guides Health Decisions for 70 Million People
A single algorithm drives an important health care decision for over 70 million people in the US. When health systems anticipate that a patient will have especially complex and intensive future health care needs, she is enrolled in a 'care management' ...
Disparate Interactions: An Algorithm-in-the-Loop Analysis of Fairness in Risk Assessments
Despite vigorous debates about the technical characteristics of risk assessments being deployed in the U.S. criminal justice system, remarkably little research has studied how these tools affect actual decision-making processes. After all, risk ...
An Empirical Study of Rich Subgroup Fairness for Machine Learning
Kearns, Neel, Roth, and Wu [ICML 2018] recently proposed a notion of rich subgroup fairness intended to bridge the gap between statistical and individual notions of fairness. Rich subgroup fairness picks a statistical fairness constraint (say, ...
The Profiling Potential of Computer Vision and the Challenge of Computational Empiricism
Computer vision and other biometrics data science applications have commenced a new project of profiling people. Rather than using 'transaction generated information', these systems measure the 'real world' and produce an assessment of the 'world state' ...
Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
- Maria De-Arteaga,
- Alexey Romanov,
- Hanna Wallach,
- Jennifer Chayes,
- Christian Borgs,
- Alexandra Chouldechova,
- Sahin Geyik,
- Krishnaram Kenthapadi,
- Adam Tauman Kalai
We present a large-scale study of gender bias in occupation classification, a task where the use of machine learning may lead to negative outcomes on peoples' lives. We analyze the potential allocation harms that can result from semantic representation ...
Equality of Voice: Towards Fair Representation in Crowdsourced Top-K Recommendations
To help their users to discover important items at a particular time, major websites like Twitter, Yelp, TripAdvisor or NYTimes provide Top-K recommendations (e.g., 10 Trending Topics, Top 5 Hotels in Paris or 10 Most Viewed News Stories), which rely on ...
Analyzing Biases in Perception of Truth in News Stories and Their Implications for Fact Checking
- Mahmoudreza Babaei,
- Abhijnan Chakraborty,
- Juhi Kulshrestha,
- Elissa M. Redmiles,
- Meeyoung Cha,
- Krishna P. Gummadi
Recently, social media sites like Facebook and Twitter have been severely criticized by policy makers, and media watchdog groups for allowing fake news stories to spread unchecked on their platforms. In response, these sites are encouraging their users ...
On Microtargeting Socially Divisive Ads: A Case Study of Russia-Linked Ad Campaigns on Facebook
- Filipe N. Ribeiro,
- Koustuv Saha,
- Mahmoudreza Babaei,
- Lucas Henrique,
- Johnnatan Messias,
- Fabricio Benevenuto,
- Oana Goga,
- Krishna P. Gummadi,
- Elissa M. Redmiles
Targeted advertising is meant to improve the efficiency of matching advertisers to their customers. However, targeted advertising can also be abused by malicious advertisers to efficiently reach people susceptible to false stories, stoke grievances, and ...
SIREN: A Simulation Framework for Understanding the Effects of Recommender Systems in Online News Environments
The growing volume of digital data stimulates the adoption of recommender systems in different socioeconomic domains, including news industries. While news recommenders help consumers deal with information overload and increase their engagement, their ...
Controlling Polarization in Personalization: An Algorithmic Framework
Personalization is pervasive in the online space as it leads to higher efficiency for the user and higher revenue for the platform by individualizing the most relevant content for each user. However, recent studies suggest that such personalization can ...
Fair Algorithms for Learning in Allocation Problems
Settings such as lending and policing can be modeled by a centralized agent allocating a scarce resource (e.g. loans or police officers) amongst several groups, in order to maximize some objective (e.g. loans given that are repaid, or criminals that are ...
Fair Allocation through Competitive Equilibrium from Generic Incomes
Two food banks catering to populations of different sizes with different needs must divide among themselves a donation of food items. What constitutes a "fair" allocation of the items among them?
Competitive equilibrium from equal incomes (CEEI) is a ...
A Moral Framework for Understanding Fair ML through Economic Models of Equality of Opportunity
We map the recently proposed notions of algorithmic fairness to economic models of Equality of opportunity (EOP)---an extensively studied ideal of fairness in political philosophy. We formally show that through our conceptual mapping, many existing ...
Beyond Open vs. Closed: Balancing Individual Privacy and Public Accountability in Data Sharing
Data too sensitive to be "open" for analysis and re-purposing typically remains "closed" as proprietary information. This dichotomy undermines efforts to make algorithmic systems more fair, transparent, and accountable. Access to proprietary data in ...
Who's the Guinea Pig?: Investigating Online A/B/n Tests in-the-Wild
A/B/n testing has been adopted by many technology companies as a data-driven approach to product design and optimization. These tests are often run on their websites without explicit consent from users. In this paper, we investigate such online A/B/n ...
Fairness-Aware Programming
Increasingly, programming tasks involve automating and deploying sensitive decision-making processes that may have adverse impacts on individuals or groups of people. The issue of fairness in automated decision-making has thus become a major problem, ...
Model Cards for Model Reporting
- Margaret Mitchell,
- Simone Wu,
- Andrew Zaldivar,
- Parker Barnes,
- Lucy Vasserman,
- Ben Hutchinson,
- Elena Spitzer,
- Inioluwa Deborah Raji,
- Timnit Gebru
Trained machine learning models are increasingly used to perform high-impact tasks in areas such as law enforcement, medicine, education, and employment. In order to clarify the intended use cases of machine learning models and minimize their usage in ...
The Social Cost of Strategic Classification
Consequential decision-making typically incentivizes individuals to behave strategically, tailoring their behavior to the specifics of the decision rule. A long line of work has therefore sought to counteract strategic behavior by designing more ...
Downstream Effects of Affirmative Action
We study a two-stage model, in which students are 1) admitted to college on the basis of an entrance exam which is a noisy signal about their qualifications (type), and then 2) those students who were admitted to college can be hired by an employer as a ...
Access to Population-Level Signaling as a Source of Inequality
We identify and explore differential access to population-level signaling (also known as information design) as a source of unequal access to opportunity. A population-level signaler has potentially noisy observations of a binary type for each member of ...
The Disparate Effects of Strategic Manipulation
When consequential decisions are informed by algorithmic input, individuals may feel compelled to alter their behavior in order to gain a system's approval. Models of agent responsiveness, termed "strategic manipulation," analyze the interaction between ...
Cited By
Recommendations
Transparency and Accountability After 2015: e-Parliament for Citizens' Engagement in the Ghanaian Environment
ICEGOV '15-16: Proceedings of the 9th International Conference on Theory and Practice of Electronic GovernanceBeyond providing information, Information and Communication Technology (ICT) really contributes to citizens' participation to public debate. With the use of ICT, Civil societies have played a big role especially in the areas of training, research, ...