Timezone: »
Following precedent in employment discrimination law, two notions of disparity are widely-discussed in papers on fairness and ML. Algorithms exhibit treatment disparity if they formally treat members of protected subgroups differently; algorithms exhibit impact disparity when outcomes differ across subgroups (even unintentionally). Naturally, we can achieve impact parity through purposeful treatment disparity. One line of papers aims to reconcile the two parities proposing disparate learning processes (DLPs). Here, the sensitive feature is used during training but a group-blind classifier is produced. In this paper, we show that: (i) when sensitive and (nominally) nonsensitive features are correlated, DLPs will indirectly implement treatment disparity, undermining the policy desiderata they are designed to address; (ii) when group membership is partly revealed by other features, DLPs induce within-class discrimination; and (iii) in general, DLPs provide suboptimal trade-offs between accuracy and impact parity. Experimental results on several real-world datasets highlight the practical consequences of applying DLPs.
Author Information
Zachary Lipton (Carnegie Mellon University)
Julian McAuley (UCSD)
Alexandra Chouldechova (CMU)
More from the Same Authors
-
2021 : Model-Free Learning for Continuous Timing as an Action »
Helen Zhou · David Childers · Zachary Lipton -
2022 : Downstream Datasets Make Surprisingly Good Pretraining Corpora »
Kundan Krishna · Saurabh Garg · Jeffrey Bigham · Zachary Lipton -
2022 : Disentangling the Mechanisms Behind Implicit Regularization in SGD »
Zachary Novack · Simran Kaur · Tanya Marwah · Saurabh Garg · Zachary Lipton -
2022 : Beyond Decision Recommendations: Stop Putting Machine Learning First and Design Human-Centered AI for Decision Support »
Zana Bucinca · Alexandra Chouldechova · Jennifer Wortman Vaughan · Krzysztof Z Gajos -
2022 : The Role of Labor Force Characteristics and Organizational Factors in Human-AI Interaction »
Lingwei Cheng · Alexandra Chouldechova -
2022 : The Challenges and Opportunities in Overcoming Algorithm Aversion in Human-AI Collaboration »
Lingwei Cheng · Alexandra Chouldechova -
2022 : RLSBench: A Large-Scale Empirical Study of Domain Adaptation Under Relaxed Label Shift »
Saurabh Garg · Nick Erickson · James Sharpnack · Alexander Smola · Sivaraman Balakrishnan · Zachary Lipton -
2022 : Local Causal Discovery for Estimating Causal Effects »
Shantanu Gupta · David Childers · Zachary Lipton -
2022 : On the Maximum Hessian Eigenvalue and Generalization »
Simran Kaur · Jeremy M Cohen · Zachary Lipton -
2022 : Panel on Technical Challenges Associated with Reliable Human Evaluations of Generative Models »
Long Ouyang · Tongshuang Wu · Zachary Lipton -
2022 Workshop: Human Evaluation of Generative Models »
Divyansh Kaushik · Jennifer Hsia · Jessica Huynh · Yonadav Shavit · Samuel Bowman · Ting-Hao Huang · Douwe Kiela · Zachary Lipton · Eric Michael Smith -
2022 Poster: Characterizing Datapoints via Second-Split Forgetting »
Pratyush Maini · Saurabh Garg · Zachary Lipton · J. Zico Kolter -
2022 Poster: Unsupervised Learning under Latent Label Shift »
Manley Roberts · Pranav Mani · Saurabh Garg · Zachary Lipton -
2022 Poster: Domain Adaptation under Open Set Label Shift »
Saurabh Garg · Sivaraman Balakrishnan · Zachary Lipton -
2020 : Contributed Talk 1: Fairness Under Partial Compliance »
Jessica Dai · Zachary Lipton -
2020 : Q & A and Panel Session with Tom Mitchell, Jenn Wortman Vaughan, Sanjoy Dasgupta, and Finale Doshi-Velez »
Tom Mitchell · Jennifer Wortman Vaughan · Sanjoy Dasgupta · Finale Doshi-Velez · Zachary Lipton -
2020 Workshop: HAMLETS: Human And Model in the Loop Evaluation and Training Strategies »
Divyansh Kaushik · Bhargavi Paranjape · Forough Arabshahi · Yanai Elazar · Yixin Nie · Max Bartolo · Polina Kirichenko · Pontus Lars Erik Saito Stenetorp · Mohit Bansal · Zachary Lipton · Douwe Kiela -
2020 Poster: A Unified View of Label Shift Estimation »
Saurabh Garg · Yifan Wu · Sivaraman Balakrishnan · Zachary Lipton -
2020 Poster: BERT Loses Patience: Fast and Robust Inference with Early Exit »
Wangchunshu Zhou · Canwen Xu · Tao Ge · Julian McAuley · Ke Xu · Furu Wei -
2019 Poster: Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift »
Stephan Rabanser · Stephan Günnemann · Zachary Lipton -
2019 Poster: Learning Robust Global Representations by Penalizing Local Predictive Power »
Haohan Wang · Songwei Ge · Zachary Lipton · Eric Xing -
2019 Poster: Game Design for Eliciting Distinguishable Behavior »
Fan Yang · Liu Leqi · Yifan Wu · Zachary Lipton · Pradeep Ravikumar · Tom M Mitchell · William Cohen -
2018 : Invited Talk 1 »
Zachary Lipton -
2018 : Panel on research process »
Zachary Lipton · Charles Sutton · Finale Doshi-Velez · Hanna Wallach · Suchi Saria · Rich Caruana · Thomas Rainforth -
2018 : Zachary Lipton »
Zachary Lipton