Fetching the paper…

Reading the bibliography…

2022

Fairness and robustness in anti-causal prediction

Makar, Maggie, D'Amour, Alexander

Original
PDF
Post on X

Understand

Robustness to distribution shift and fairness have independently emerged as two important desiderata required of modern machine learning models.

While these two desiderata seem related, the connection between them is often unclear in practice.
Here, we discuss these connections through a causal lens, focusing on anti-causal prediction tasks, where the input to a classifier (e.g., an image) is assumed to be generated as a function of the target label and the protected attribute.
By taking this perspective, we draw explicit connections between a common fairness criterion - separation - and a common notion of robustness - risk invariance.

Fairness and robustness in anti-causal prediction · Around

Built on

Learning bounds for importance weighting
Corinna Cortes, Yishay Mansour, and Mehryar Mohri · 2010
Earlier work this paper cites.
A kernel two-sample test
Arthur Gretton, Karsten M Borgwardt, Malte J Rasch, Bernhard Schölkopf, and Alexander Smola · 2012
Earlier work this paper cites.
TensorFlow: Large-scale machine learning on heterogeneous systems, 2015
Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dandelion Mané, Rajat Monga, Sherry Moore, Derek Murray, Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda Viégas, Oriol Vinyals, Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng · 2015
Earlier work this paper cites.
The variational fair autoencoder
Original
Christos Louizos, Kevin Swersky, Yujia Li, Max Welling, and Richard Zemel · 2015
Earlier work this paper cites.
Equality of opportunity in supervised learning
Moritz Hardt, Eric Price, and Nati Srebro · 2016
Earlier work this paper cites.
Algorithmic decision making and the cost of fairness
Sam Corbett-Davies, Emma Pierson, Avi Feller, Sharad Goel, and Aziz Huq · 2017
Earlier work this paper cites.
Densely connected convolutional networks
Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger · 2017
Earlier work this paper cites.
Avoiding discrimination through causal reasoning
Niki Kilbertus, Mateo Rojas-Carulla, Giambattista Parascandolo, Moritz Hardt, Dominik Janzing, and Bernhard Schölkopf · 2017
Earlier work this paper cites.
Counterfactual fairness
Original
Matt J Kusner, Joshua R Loftus, Chris Russell, and Ricardo Silva · 2017
Earlier work this paper cites.
Why do deep convolutional networks generalize so poorly to small image transformations?
Original
Aharon Azulay and Yair Weiss · 2018
Earlier work this paper cites.
Recognition in terra incognita
Sara Beery, Grant Van Horn, and Pietro Perona · 2018
Earlier work this paper cites.
Generalisation in humans and deep neural networks
Robert Geirhos, Carlos RM Temme, Jonas Rauber, Heiko H Schütt, Matthias Bethge, and Felix A Wichmann · 2018
Earlier work this paper cites.
Eddie murphy and the dangers of counterfactual causal thinking about detecting racial discrimination
Issa Kohler-Hausmann · 2018
Earlier work this paper cites.

Similar

Learning adversarially fair and transferable representations
Original
David Madras, Elliot Creager, Toniann Pitassi, and Richard Zemel · 2018
Cited alongside, same era.
Fair inference on outcomes
Razieh Nabi and Ilya Shpitser · 2018
Cited alongside, same era.
Fairness in decision-making—the causal explanation formula
Junzhe Zhang and Elias Bareinboim · 2018
Cited alongside, same era.
Invariant risk minimization
Original
Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, and David Lopez-Paz · 2019
Cited alongside, same era.
Fairness and Machine Learning
Solon Barocas, Moritz Hardt, and Arvind Narayanan · 2019
Cited alongside, same era.
Path-specific counterfactual fairness
Silvia Chiappa · 2019

Then

Underspecification presents challenges for credibility in modern machine learning
Original
Alexander D’Amour, Katherine Heller, Dan Moldovan, Ben Adlam, Babak Alipanahi, Alex Beutel, Christina Chen, Jonathan Deaton, Jacob Eisenstein, Matthew D Hoffman, et al · 2020
Later among the works it cites.
Shortcut learning in deep neural networks
Original
Robert Geirhos, Jörn-Henrik Jacobsen, Claudio Michaelis, Richard Zemel, Wieland Brendel, Matthias Bethge, and Felix A Wichmann · 2020
Later among the works it cites.
Deep learning applied to chest x-rays: Exploiting and preventing shortcuts
Sarah Jabbour, David Fouhey, Ella Kazerooni, Michael W Sjoding, and Jenna Wiens · 2020
Later among the works it cites.
An investigation of why overparameterization exacerbates spurious correlations
Original
Shiori Sagawa, Aditi Raghunathan, Pang Wei Koh, and Percy Liang · 2020
Later among the works it cites.
Environment inference for invariant learning

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Cited alongside, same era.

50 years of test (un) fairness: Lessons for machine learning

Ben Hutchinson and Margaret Mitchell · 2019

Cited alongside, same era.

Adversarial examples are not bugs, they are features

Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, and Aleksander Madry · 2019

Cited alongside, same era.

Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison

Jeremy Irvin, Pranav Rajpurkar, Michael Ko, Yifan Yu, Silviana Ciurea-Ilcus, Chris Chute, Henrik Marklund, Behzad Haghgoo, Robyn Ball, Katie Shpanskaya, et al · 2019

Cited alongside, same era.

H chi, jilin chen, and alex beutel. 2019

Flavien Prost and Hai Qian · 2019

Cited alongside, same era.

Toward a better trade-off between performance and fairness with kernel-based distribution matching

Flavien Prost, Hai Qian, Qiuwen Chen, Ed H Chi, Jilin Chen, and Alex Beutel · 2019

Cited alongside, same era.

Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization

Original

Shiori Sagawa, Pang Wei Koh, Tatsunori B Hashimoto, and Percy Liang · 2019

Cited alongside, same era.

Elliot Creager, Joern-Henrik Jacobsen, and Richard Zemel · 2021

Later among the works it cites.

Out-of-distribution prediction with invariant risk minimization: The limitation and an effective fix

Ruocheng Guo, Pengchuan Zhang, Hao Liu, and Emre Kiciman · 2021

Later among the works it cites.

Chextransfer: performance and parameter efficiency of imagenet models for chest x-ray interpretation

Alexander Ke, William Ellsworth, Oishi Banerjee, Andrew Y Ng, and Pranav Rajpurkar · 2021

Later among the works it cites.

Out-of-distribution generalization via risk extrapolation (rex)

David Krueger, Ethan Caballero, Joern-Henrik Jacobsen, Amy Zhang, Jonathan Binas, Dinghuai Zhang, Remi Le Priol, and Aaron Courville · 2021

Later among the works it cites.

Causally-motivated shortcut removal using auxiliary labels

Maggie Makar, Ben Packer, Dan Moldovan, Davis Blalock, Yoni Halpern, and Alexander D’Amour · 2021

Later among the works it cites.

Algorithmic fairness: Choices, assumptions, and definitions

Shira Mitchell, Eric Potash, Solon Barocas, Alexander D’Amour, and Kristian Lum · 2021

Later among the works it cites.

Does robustness improve fairness? approaching fairness with word substitution robustness methods for text classification

Yada Pruksachatkun, Satyapriya Krishna, Jwala Dhamala, Rahul Gupta, and Kai-Wei Chang · 2021

Later among the works it cites.

Counterfactual invariance to spurious correlations: Why and how to pass stress tests

Victor Veitch, Alexander D’Amour, Steve Yadlowsky, and Jacob Eisenstein · 2021

Later among the works it cites.