Papers in the proceedings are sorted by sessions. A public folder with the presentations will be available.

Tuesday, January 28th, 2020

Session 1: Accountability

Session chair: Michael Veale

What to account for when accounting for algorithms: A systematic literature review on algorithmic accountability

M. Wieringa

Algorithmic Realism: Expanding the Boundaries of Algorithmic Thought

B. Green; S. Viljoen

Algorithmic Accountability in Public Administration: The GDPR Paradox

S. Kang

Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing

D. Raji; A. SMART; R. White; M. Mitchell; T. Gebru; B. Hutchinson; J. Smith-Loud; D. Theron; P. Barnes

Toward Situated Interventions for Algorithmic Equity: Lessons from the Field

M. Katell, M. Young, B. Herman, D. Dailey, V. Guetler, A. Tam, C. Binz, D. Raz, P. Krafft

Session 2: Explainability 1

Session chair: Jatinder Singh

Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches

K. Sokol; P. Flach

Multi-layered Explanation from Algorithmic Impact Assessments in the GDPR

G. Malgieri; M. Kaminski

The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons

S. Barocas; A. Selbst; M. Raghavan

Why Does My Model Fail? Contrastive Local Explanations for Retail Forecasting

A. Lucic; H. Haned; M. de Rijke

The Human Body is a Black Box: Supporting Clinical Decision-Making with Deep Learning

M. Sendak; M. Elish; M. Gao; W. Ratliff; M. Nichols; J. Futoma; A. Bedoya; S. Balu; C. O'Brien

Session 3: Auditing/Assessment 1

Session chair: Suresh Venkatasubramanian

Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination

N. Kallus; X. Mao; A. Zhou

FlipTest: Fairness Testing via Optimal Transport

E. Black; S. Yeom; M. Fredrikson

Implications of AI (Un-)Fairness in Higher Education Admissions: The Effects of Perceived AI (Un-)Fairness on Exit, Voice and Organizational Reputation

F. Marcinkowski, K. Kieslich, C. Starke, M. Lünich

Auditing Radicalization Pathways on YouTube

M. Ribeiro; R. Ottoni; R. West; V. Almeida; W. Meira Jr.

Case Study: Predictive Fairness to Reduce Misdemeanor Recidivism Through Social Service Interventions

K. Rodolfa; E. Salomon; L. Haynes; I. Mendieta; J. Larson; R. Ghani

Session 4: Fairness 1

Session chair: Solon Barocas

The concept of fairness in the GDPR: a linguistic and contextual interpretation

G. Malgieri

Studying Up: Reorienting the study of algorithmic fairness around issues of power

C. Barabas; C. Doyle; J. Rubinovitz; K. Dinakar

POTs: Protective Optimization Technologies

R. Overdorf; B. Kulynych; E. Balsa; C. Troncoso; S. Gürses

Fair Decision Making using Privacy-Protected Data

S. Kuppam; R. McKenna; D. Pujol; M. Hay; A. Machanavajjhala; G. Miklau

Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data

D. Slack; S. Friedler; E. Givental

Session 5: Ethics and Policy

Session chair: Lilian Edwards

From Ethics Washing to Ethics Bashing: A View on Tech Ethics from Within Moral Philosophy

E. Bietti

Onward for the freedom of others: Marching beyond the AI Ethics

P. Terzis

Whose Side are Ethics Codes On? Power, Responsibility and the Social Good

A. Washington, R. Kuo

Algorithmic Targeting of Social Policies: Fairness, Accuracy, and Distributed Governance

A. Noriega-Campero, B. Bulle-Bueno, L. Cantu, M. Bakker, L. Tejerina, A. Pentland

Roles for Computing in Social Change

R. Abebe; S. Barocas; J. Kleinberg; K. Levy; M. Raghavan; D. Robinson

Session 6: Values

Session chair: Gabriela Zanfir-Fortuna

Regulating Transparency? Facebook, Twitter and the German Network Enforcement Act

B. Wagner, K. Rozgonyi, M. Sekwenz, J. Singh, J. Cobbe

The relationship between trust in AI and trustworthy machine learning technologies

E. Toreini; M. Aitken; A. van Moorsel; K. Elliott; K. Coopamootoo

The philosophical basis of algorithmic recourse

S. Venkatasubramanian; M. Alfano

Value-laden Disciplinary Shifts in Machine Learning

R. Dotan; S. Milli

Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making

Y. Zhang; Q. Liao; R. Bellamy

Session 7: Data Collection

Session chair: Brent Hecht

Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learning

E. Jo; T. Gebru

Data in New Delhi's predictive policing system

V. Marda; S. Narayan

Garbage In, Garbage Out: Do Machine Learning Application Papers in Social Computing Report Where Human-Labeled Training Data Comes From?

R. Geiger, K. Yu, Y. Yang, M. Dai, J. Qiu, R. Tang, J. Huang

Wesnesday, January 29th, 2020

Session 8: Fairness 2

Session chair: Sorelle Friedler

Bidding Strategies with Gender Nondiscrimination Constraints for Online Ad Auctions

M. Nasr, M. Tschantz

Multi-category Fairness in Sponsored Search Auctions

C. Ilvento; M. Jagadeesan; S. Chawla

Reducing Sentiment Polarity for Demographic Attributes in Word Embeddings using Adversarial Learning

C. Sweeney; M. Najafian

Interventions for Ranking in the Presence of Implicit Bias

A. Mehrotra; L. Celis; N. Vishnoi

The Disparate Equilibria of Algorithmic Decision Making when Individuals Invest Rationally

L. Liu; A. Wilson; N. Haghtalab; A. Kalai; C. Borgs; J. Chayes

Session 9: Cognition and Education

Session chair: Elana Zeide

An Empirical Study on the Perceived Fairness of Realistic, Imperfect Machine Learning Models

G. Harrison, J. Hanson, C. Jacinto, J. Ramirez, B. Ur

Artificial mental phenomena: Psychophysics as a framework to detect perception biases in AI models

L. Liang, D. Acuna

The Social Lives of Generative Adversarial Networks

M. Castelle

Towards a more representative politics in the ethics of computer science

J. Moore

Integrating FATE/Critical Data Studies into Data Science curricula: where are we going and how do we get there?

J. Bates; D. Cameron; A. Checco; P. Clough; F. Hopfgartner; S. Mazumdar; L. Sbaffi; P. Stordy; A. de León

Session 10: Auditing/Assessment 2

Session chair: Michael Ekstrand

Recommendations and User Agency: The Reachability of Collaboratively-Filtered Information

S. Dean; S. Rich; B. Recht

Bias in word embeddings

O. Papakyriakopoulos; S. Hegelich; J. Serrano; F. Marco

What does it mean to ‘solve’ the problem of discrimination in hiring? Social, technical and legal perspectives from the UK on automated hiring systems

J. Sánchez-Monedero, L. Dencik, L. Edwards

Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices

M. Raghavan; S. Barocas; J. Kleinberg; K. Levy

The impact of overbooking on a pre-trial risk assessment tool

K. Lum; C. Boudin; M. Price

Session 11: Sensitive Attributes

Session chair: Maya Ganesh

Awareness in Practice: Tensions in Access to Sensitive Attribute Data for Antidiscrimination

A. Rieke; M. Bogen; S. Ahmed

Towards a Critical Race Methodology in Algorithmic Fairness

E. Denton; A. Hanna; J. Smith-Loud; A. Smart

What’s Sex Got to Do With Fair Machine Learning?

L. Hu, I. Kohler-Hausmann

Thursday, January 30th, 2020

Session 12: Fairness 3

Session chair: Kristian Lum

On the Apparent Conflict Between Individual and Group Fairness

R. Binns

Fairness Is Not Static: Deeper Understanding of Long Term Fairness via Agents and Environments

A. D'Amour; Y. Halpern; H. Srinivasan; P. Baljekar; J. Atwood; D. Sculley

Fair Classification and Social Welfare

L. Hu; Y. Chen

Preference-Informed Fairness

M. Kim; A. Korolova; G. Rothblum; G. Yona

Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy

K. Yang, K. Qinami, L. Fei-Fei, J. Deng, O. Russakovsky

Session 13: Auditing/Assessment 3

Session chair: Timnit Gebru

The Case for Voter-Centered Audits of Search Engines during Political Elections

E. Mustafaraj; E. Lurie; C. Devine

Whose Tweets are Surveilled for the Police: An Audit of a Social-Media Monitoring Tool via Log Files

G. Borradaile; B. Burkhardt; A. LeClerc

Dirichlet uncertainty wrappers for actionable algorithm accuracy accountability and auditability

J. Mena Roldán; O. Pujol Vila; J. Vitrià Marca

Counterfactual Risk Assessments, Evaluation, and Fairness

A. Coston, A. Chouldechova, E. Kennedy, A. Mishler

The False Promise of Risk Assessments: Epistemic Reform and the Limits of Fairness

B. Green

Session 14: Explainability 2

Session chair: Anna Monreale

Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations

R. Mothilal; A. Sharma; C. Tan

Model Agnostic Interpretability of Text Rankers via Intent Modelling

J. Singh, A. Anand

Doctor XAI: An ontology-based approach to black-box sequential data classification explanations

C. Panigutti; A. Perotti; D. Pedreschi

Robustness in Machine Learning Explanations:Does it Matter?

L. Hancox-Li

Explainable Machine Learning in Deployment

U. Bhatt, A. Xiang, S. Sharma, A. Weller, A. Taly, Y. Jia, J. Ghosh, R. Puri, J. Moura, P. Eckersley

Session 15: Fairness 4

Session chair: Reuben Binns

Fairness and Utilization in Allocating Resources with Uncertain Demand

K. Donahue; J. Kleinberg

The Effects of Competition and Regulation on Error Inequality in Data-Driven Markets

H. Elzayn; B. Fish

Measuring Justice in Machine Learning

A. Lundgard


Best Paper Awards

  • Best Paper Award (CS): Fairness and Utilization in Allocating Resources with Uncertain Demand by Kate Donahue and Jon Kleinberg
  • Best Student Paper Award (CS): Why Does My Model Fail? Contrastive Local Explanations for Retail Forecasting by Ana Lucic, Hinda Haned, and Maarten de Rijke
  • Best Paper Award (SSH/LAW/EDU/PE): What does it mean to ‘solve’ the problem of discrimination in hiring? by Javier Sánchez-Monedero, Lina Dencik, and Lilian Edwards
  • Best Student Paper Award (SSH/LAW/EDU/PE): What to account for when accounting for algorithms: A systematic literature review on algorithmic accountability by Maranke Wieringa