-
Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach
Vijay Keswani, Anay Mehrotra, L. Elisa Celis
ICML 2024 [code] -
Algorithmic Fairness From the Perspective of Legal Anti-discrimination Principles
Vijay Keswani, L. Elisa Celis
AIES 2024 -
Subset Selection Based On Multiple Rankings in the Presence of Bias: Effectiveness of Fairness Constraints for Multiwinner Voting Score Functions
Niclas Boehmer, L. Elisa Celis, Lingxiao Huang, Anay Mehrotra, and Nisheeth K. Vishnoi
ICML 2023 [code] -
Maximizing Submodular Functions for Recommendation in the Presence of Biases
Anay Mehrotra and Nisheeth K. Vishnoi
The Web Conference (formerly WWW) 2023 [code] [video] -
Addressing Strategic Manipulation Disparities in Fair Classification
Vijay Keswani, L. Elisa Celis
EAAMO 2023 -
Diverse Representation via Computational Participatory Elections – Lessons from a Case Study
Florian Evéquoz, Johan Rochel, Vijay Keswani, L. Elisa Celis
EAAMO 2022 -
Fair Ranking with Noisy Protected Attributes
Anay Mehrotra and Nisheeth K. Vishnoi
NeurIPS 2022 [code] [video] -
Revisiting Group Fairness Metrics: The Effect of Networks
Anay Mehrotra, Jeffrey Sachs, and L. Elisa Celis
CSCW 2022 [video] -
Selection in the Presence of Implicit Bias: The Advantage of Intersectional Constraints
Anay Mehrotra, Bary S. R. Pradelski, and Nisheeth K. Vishnoi
ACM FAccT 2022 [short-video] [long-video] -
Fairness for AUC via Feature Augmentation
Hortense Fong, Vineet Kumar, Anay Mehrotra, Nisheeth K. Vishnoi
ACM FAccT 2022 [short-video] [long-video] -
Fair Classification with Adversarial Perturbations
L. Elisa Celis, Anay Mehrotra, Nisheeth K. Vishnoi
NeurIPS 2021 [code] [video] -
Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees
L. Elisa Celis, Lingxiao Huang, Vijay Keswani, Nisheeth K. Vishnoi
ICML 2021 [code] -
Auditing for Diversity using Representative Examples
Vijay Keswani, L. Elisa Celis
ACM SIGKDD 2021 -
Towards Unbiased and Accurate Deferral to Multiple Experts
Vijay Keswani, Matthew Lease, Krishnaram Kenthapadi
AIES 2021 -
Dialect Diversity in Text Summarization on Twitter
Vijay Keswani, L. Elisa Celis
The Web Conference (formerly WWW) 2021 -
Mitigating Bias in Set Selection with Noisy Protected Attributes
Anay Mehrotra, L. Elisa Celis
ACM FAccT 2021 [code] [video] -
The Effect of the Rooney Rule on Implicit Bias in the Long Term
L. Elisa Celis, Chris Hays, Anay Mehrotra, Nisheeth K. Vishnoi
ACM FAccT 2021 [demo] [demo-code] [video] -
Implicit Diversity in Image Summarization
L. Elisa Celis, Vijay Keswani
CSCW 2020 -
Data Preprocessing to Mitigate Bias: A Maximum Entropy-based Approach
L. Elisa Celis, Vijay Keswani, Nisheeth K. Vishnoi
ICML 2020 [blogpost] [code] -
Towards Just, Fair and Interpretable Methods for Judicial Subset Selection
Lingxiao Huang, Julia Wei, L. Elisa Celis
AIES 2020 -
Interventions for Ranking in the Presence of Implicit Bias
L. Elisa Celis, Anay Mehrotra, Nisheeth K. Vishnoi
ACM FAccT (formerly FAT*) 2020 [video] [code] -
Assessing Social and Intersectional Biases in Contextualized Word Representations
Yi Chern Tan, L. Elisa Celis
NeurIPS 2019 -
Coresets for Clustering with Fairness Constraints
Lingxiao Huang, Shaofeng Jiang, Nisheeth K. Vishnoi
NeurIPS 2019 -
Towards Controlling Discrimination in Online Ad Auctions
L. Elisa Celis, Anay Mehrotra, Nisheeth K. Vishnoi
ICML 2019 [demo] [methodology] [code] [video: 26m-31m]
(Also best student paper in 3rd Workshop on Mechanism Design for Social Good 2019) -
Stable and Fair Classification
Lingxiao Huang, Nisheeth K. Vishnoi
ICML 2019 [code] -
A Dashboard for Controlling Polarization in Personalization
L. Elisa Celis, Sayash Kapoor, Farnood Salehi, Vijay Keswani, Nisheeth K. Vishnoi
Invited paper in AI Communications 2019 [demo] [methodology]
(Previously in IJCAI-ECAI 2018) -
Controlling Polarization in Personalization
L. Elisa Celis, Sayash Kapoor, Farnood Salehi, Nisheeth K. Vishnoi
Best technical paper - ACM FAccT (formerly FAT*) 2019 [video: 19m-29m] -
Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees
L. Elisa Celis, Lingxiao Huang, Vijay Keswani, Nisheeth K. Vishnoi
ACM FAccT (formerly FAT*) 2019 [blogpost] [code] [video: 11m-21m] -
Fair and Diverse DPP-based Data Summarization
L. Elisa Celis, Vijay Keswani, Damian Straszak, Amit Deshpande, Tarun Kathuria, Nisheeth K. Vishnoi
ICML 2018 [demo] [code] [video] -
Multiwinner Voting with Fairness Constraints
L. Elisa Celis, Lingxiao Huang, Nisheeth K. Vishnoi
IJCAI-ECAI 2018 [demo] [blogpost] [code] -
Ranking with Fairness Constraints
L. Elisa Celis, Damian Straszak, Nisheeth K. Vishnoi
ICALP 2018 [demo] [methodology] -
On the Complexity of Constrained Determinantal Point Processes
L. Elisa Celis, Amit Deshpande, Tarun Kathuria, Damian Straszak, Nisheeth K. Vishnoi
APPROX-RANDOM 2018 -
Fair Personalization
L. Elisa Celis, Nisheeth K. Vishnoi
FAT ML 2017 -
How to be Fair and Diverse?
L. Elisa Celis, Amit Deshpande, Tarun Kathuria, Nisheeth K. Vishnoi
FAT ML 2016 [video]
The use of standard datasets, models, and algorithms often incorporates and exacerbates social biases in systems that use machine learning and artificial intelligence. Context-aware design and implementation of automated decision making algorithms is, therefore, an important and necessary venture. Our group aims to mitigate social biases in AI, with a focus on providing feasible debiased alternatives to currently-used models.
People
Faculty - Elisa Celis, Nisheeth VishnoiContributors - Chris Hays, Lingxiao Huang, Vijay Keswani, Anay Mehrotra, Damian Straszak, Yi-Chern Tan, Julia Wei
Demos
Multiwinner Voting
Elect a committee that is balanced across different attribute types. Deployed in Swiss elections. [Video]
Ranking
Prototype for gender-balanced rankings with applications to search engines, newsfeeds, and recommendation systems.
Classification
Python notebook for a meta fair classification algorithm, works for various fairness metrics. Deployed in IBM AIF 360.
Debiasing Data
Python notebook for learning and evaluating unbiased maximum-entropy distributions from biased datasets.