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
-
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
