Jump to full list, reports, blogs and popular press.
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.
Ke Yang, Julia Stoyanovich, Abolfazl Asudeh, Bill Howe, HV Jagadish and Gerome Miklau
Proceedings of ACM SIGMOD (demo), 2018
Selection algorithms usually score individual items in isolation, and then select the top scoring items. However, often there is an additional diversity objective. Since diversity is a group property, it does not easily jibe with individual item scoring.
Julia Stoyanovich, Ke Yang and HV Jagadish
To facilitate collaboration over sensitive data, we present DataSynthesizer, a tool that takes a sensitive dataset as input and generates a structurally and statistically similar synthetic dataset with strong privacy guarantees.
Haoyue Ping, Julia Stoyanovich and Bill Howe
We see a need for a data sharing and collaborative analytics platform with features to encourage (and in some cases, enforce) best practices at all stages of the data science lifecycle. We propose Fides, in the context of urban analytics, outlining a systems research agenda in responsible data science.
Bill Howe, Julia Stoyanovichi, Serge Abiteboul, Gerome Miklau, Arnaud Sahuguet and Gerhard Weikum
Teaching Responsible Data Science: Charting New Pedagogical Territory
Julia Stoyanovich and Armanda Lewis
International Journal of Artificial Intelligence in Education (IJAIED), 2021
Causal Intersectionality and Fair Ranking
Ke Yang, Joshua R. Loftus, and Julia Stoyanovich
Algorithmic Techniques for Necessary and Possible Winners
Vishal Chakraborty, Theo Delemazure, Benny Kimelfeld, Phokion G. Kolaitis, Kunal Relia, and Julia Stoyanovich
ACM/IMS Transactions on Data Science
Lightweight Inspection of Data Preprocessing in Native Machine Learning Pipelines
Stefan Grafberger, Julia Stoyanovich, and Sebastian Schelter
Taming Technical Bias in Machine Learning Pipelines
Sebastian Schelter and Julia Stoyanovich
IEEE Data Engineering Bulletin 43(4): 2020
Fairness in Ranking: A Survey
Meike Zehlike, Ke Yang, and Julia Stoyanovich
Impact Remediation: Optimal Interventions to Reduce Inequality
Lucius E. J. Bynum, Joshua R. Loftus, and Julia Stoyanovich
Fairness as Equality of Opportunity: Normative Guidance from Political Philosophy
Falaah Arif Khan, Eleni Manis, and Julia Stoyanovich
Fairness and Friends
Falaah Arif Khan, Eleni Manis, and Julia Stoyanovich
ACM FAccT (2021), tutorial slides
Responsible Data Management
Julia Stoyanovich, Bill Howe, and H.V. Jagadish
PVLDB 13(12): 3474-3489 (2020), invited paper accompanying VLDB 2020 keynote presentation
The Imperative of Interpretable Machines
Julia Stoyanovich, Jay J. Van Bavel, and Tessa V. West
Nature Machine Intelligence, April 2020
Fairness-Aware Instrumentation of Preprocessing Pipelines for Machine Learning
Ke Yang, Biao Huang, Julia Stoyanovich, and Sebastian Schelter
Proceedings of HILDA 2020 (an ACM SIGMOD workshop)
FairPrep: Promoting Data to a First-Class Citizen in Studies on Fairness-Enhancing Interventions
Sebastian Schelter, Yuxuan He, Jatin Khilnani, and Julia Stoyanovich
EDBT 2020 (short paper), arXiv, November 2019, EDBT talk video
Balanced Ranking with Diversity Constraints
Ke Yang, Vasilis Gkatzelis, and Julia Stoyanovich
Designing Fair Ranking Schemes
Abolfazl Asudeh, H. V. Jagadish, Julia Stoyanovich, and Gautam Das
Proceedings of ACM SIGMOD, 2019
MithraRanking: A System for Responsible Ranking Design (demonstration)
Yifan Guan, Abolfazl Asudeh, Pranav Mayuram, H. V. Jagadish, Julia Stoyanovich, Gerome Miklau, and Gautam Das
Proceedings of ACM SIGMOD, 2019
Transparency, Fairness, Data Protection, Neutrality: Data Management Challenges in the Face of New Regulation
Serge Abiteboul and Julia Stoyanovich
ACM Journal of Data and Information Quality, 2019
Nutritional Labels for Data and Models
Julia Stoyanovich and Bill Howe
IEEE Data Engineering Bulletin 42(3): 13-23 (2019)
Towards Responsible Data-driven Decision Making in Score-Based Systems
Abolfazl Asudeh, H. V. Jagadish, and Julia Stoyanovich
IEEE Data Engineering Bulletin 42(3): 76-87 (2019)
TransFAT: Translating Fairness, Accountably and Transparency into Data Science Practice
Julia Stoyanovich
International Workshop on Processing Information Ethically (PIE@CAiSE) (2019)
On Obtaining Stable Rankings
Abolfazl Asudeh, H. V. Jagadish, Gerome Miklau, and Julia Stoyanovich
Panel: A Debate on Data and Algorithmic Ethics
Julia Stoyanovich, Bill Howe, H. V. Jagadish, Gerome Miklau
PVLDB 11(12): 2165-2167 (2018)
Research Directions for Principles of Data Management (Dagstuhl Perspectives Workshop 16151)
Serge Abiteboul, Marcelo Arenas, Pablo Barceló, Meghyn Bienvenu, Diego Calvanese, Claire David, Richard Hull, Eyke Hüllermeier, Benny Kimelfeld, Leonid Libkin, Wim Martens, Tova Milo, Filip Murlak, Frank Neven, Magdalena Ortiz, Thomas Schwentick, Julia Stoyanovich, Jianwen Su, Dan Suciu, Victor Vianu, Ke Yi
Dagstuhl Manifestos 7(1): 1-29 (2018)
A Technical Research Agenda in Data Ethics and Responsible Data Management
Julia Stoyanovich, Bill Howe, and HV Jagadish
Proceedings of ACM SIGMOD, 2018
RC-Index: Diversifying Answers to Range Queries
Yue Wang, Alexandra Meliou, and Gerome Miklau
A Nutritional Label for Rankings
Ke Yang, Julia Stoyanovich, Abolfazl Asudeh, Bill Howe, HV Jagadish and Gerome Miklau
Proceedings of ACM SIGMOD (demo), 2018
Online Set Selection with Fairness and Diversity Constraints
Julia Stoyanovich, Ke Yang and HV Jagadish
MobilityMirror: Bias-Adjusted Synthetic Transportation Datasets
Luke Rodriguez, Babak Salimi, Haoyue Ping, Julia Stoyanovich and Bill Howe
Diversity in Big Data: A Review
Marina Drosou, HV Jagadish, Evaggelia Pitoura and Julia Stoyanovich
Big Data Special Issue on Social and Technical Trade-Offs, June 2017
Measuring fairness in ranked outputs
Ke Yang and Julia Stoyanovich
DataSynthesizer: Privacy-preserving synthetic datasets
Haoyue Ping, Julia Stoyanovich and Bill Howe
Fides: A platform for responsible data science
Bill Howe, Julia Stoyanovichi, Serge Abiteboul, Gerome Miklau, Arnaud Sahuguet and Gerhard Weikum
Data, responsibly: fairness, neutrality and transparency in data analysis
Julia Stoyanovich, Serge Abiteboul and Gerome Miklau
Collaborative Access Control in WebdamLog
Vera Zaychik Moffitt, Julia Stoyanovich, Serge Abiteboul, Gerome Miklau
Proceedings of ACM SIGMOD, 2015
Rule-Based Application Development using Webdamlog
Serge Abiteboul, Emilien Antoine, Gerome Miklau, Julia Stoyanovich, and Jules Testard
Making Interval-Based Clustering Rank-Aware
Julia Stoyanovich, Sihem Amer-Yahia and Tova Milo
On Provenance and Privacy
Susan Davidson, Sanjeev Khanna, Sudeepa Roy, Julia Stoyanovich, Val Tannen, Yi Chen
Data, Responsibly (Dagstuhl Seminar 16291)
Serge Abiteboul, Gerome Miklau, Julia Stoyanovich and Gerhard Weikum
Schloss Dagstuhl Seminar Report 2016
Research Directions for Principles of Data Management (Dagstuhl Perspectives Workshop 16151)
Serge Abiteboul, Marcelo Arenas, Pablo Barceló, Meghyn Bienvenu, Diego Calvanese, Claire David, Richard Hull, Eyke Hüllermeier, Benny Kimelfeld, Leonid Libkin, Wim Martens, Tova Milo, Filip Murlak, Frank Neven, Magdalena Ortiz, Thomas Schwentick, Julia Stoyanovich, Jianwen Su, Dan Suciu, Victor Vianu, Ke Yi
Schloss Dagstuhl Seminar Report 2016 (full), SIGMOD Record (abridged)
Testimony of Julia Stoyanovich before the New York City Department of Consumer and Worker Protection regarding Local Law 144 of 2021 in Relation to Automated Employment Decision Tools
Julia Stoyanovich June 6, 2022
We need laws to take on racism and sexism in hiring technology
Alexandra Reeve Givens, Hilke Schellmann, and Julia Stoyanovich New York Times, March 17, 2021
Public Engagement Showreel, Int 1894
NYU Center for Responsible AI December 15, 2020
Testimony of Julia Stoyanovich before New York City Council Committee on Technology regarding Int 1894-2020, Sale of automated employment decision tools
Julia Stoyanovich November 12, 2020
Testimony of Julia Stoyanovich and Solon Barocas before New York City Council Committee on Technology, regarding Update on Local Law 49 of 2018 in Relation to Automated Decision Systems (ADS) Used by Agencies
Julia Stoyanovich and Solon Barocas April 4, 2019
Testimony of Julia Stoyanovich before New York City Council Committee on Technology and the Commission on Public Information and Communication (COPIC)
February 12, 2019
Follow the Data! Algorithmic Transparency Starts with Data Transparency
Julia Stoyanovich and Bill Howe The Ethical Machine, November 27, 2018
An Algorithmic Approach to Correct Bias in Urban Transportation Datasets
October 30, 2018
NYC Has An Algorithm Ethics Task Force, And Drexel Prof Julia Stoyanovich Is Involved
May 30, 2018
Testimony of Julia Stoyanovich before the New York City Council Committee on Technology regarding Automated Processing of Data (Int. 1696-2017)
October 16, 2017
Refining the Concept of a Nutritional Label for Data and Models
Julia Stoyanovich and Bill Howe Freedom to Tinker, Princeton CITP
University Researchers Use ‘Fake’ Data for Social Good
Bill Howe November 7, 2017
Julia Stoyanovich on the importance of many perspectives at the Data for Good Exchange
Tech at Bloomberg, July 7, 2017
Plaidoyer pour une analyse responsable des données
Serge Abiteboul and Julia Stoyanovich Le Monde, October 12, 2015
Revealing Algorithmic Rankers
Julia Stoyanovich and Ellen P. Goodman Freedom to Tinker, Princeton CITP
The Data, Responsibly Manifesto
Serge Abiteboul and Julia Stoyanovich ACM SIGMOD blog