Timezone: »

 
Poster
On Learning Fairness and Accuracy on Multiple Subgroups
Changjian Shui · Gezheng Xu · Qi CHEN · Jiaqi Li · Charles Ling · Tal Arbel · Boyu Wang · Christian Gagné

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #442

We propose an analysis in fair learning that preserves the utility of the data while reducing prediction disparities under the criteria of group sufficiency. We focus on the scenario where the data contains multiple or even many subgroups, each with limited number of samples. As a result, we present a principled method for learning a fair predictor for all subgroups via formulating it as a bilevel objective. Specifically, the subgroup specific predictors are learned in the lower-level through a small amount of data and the fair predictor. In the upper-level, the fair predictor is updated to be close to all subgroup specific predictors. We further prove that such a bilevel objective can effectively control the group sufficiency and generalization error. We evaluate the proposed framework on real-world datasets. Empirical evidence suggests the consistently improved fair predictions, as well as the comparable accuracy to the baselines.

Author Information

Changjian Shui (McGill University)
Gezheng Xu (University of Western Ontario)
Qi CHEN (Laval University)
Jiaqi Li (University of Western Ontario)
Charles Ling (University of Western Ontario)
Tal Arbel (McGill University)
Boyu Wang (University of Western Ontario)
Christian Gagné (Université Laval)

Christian Gagné is a professor at the Electrical Engineering and Computer Engineering Department of Université Laval since 2008. He is the director of the Institute Intelligence and Data (IID) of l’Université Laval. He holds a Canada-CIFAR Artificial Intelligence Chair and is an associate member to Mila. He is also a member of the Computer Vision and Systems Laboratory (CVSL), a component of the Robotics, Vision and Machine Intelligence Research Centre (CeRVIM), and the Big Data Research Centre (BDRC) of Université Laval. He is also participating to the REPARTI and UNIQUE strategic clusters of the FRQNT, the VITAM FRQS center and the International Observatory on the Societal Impacts of AI (OBVIA). He completed a PhD in Electrical Engineering (Université Laval) in 2005 and then had a postdoctoral stay jointly at INRIA Saclay (France) and the University of Lausanne (Switzerland) in 2005-2006. He worked as research associate in the industry between 2006 and 2008. He is a member of executive board the ACM Special Interest Group on Evolutionary Computation (SIGEVO) since 2017. His research interests are on the development of methods for machine learning and stochastic optimization. In particular, he is interested by deep neural networks, representation learning and transfer, meta-learning and multitask learning. He is also interested by optimization approaches based on probabilistic models and evolutionary algorithms for black-box optimization and automatic programming, among others. A significant share of his research work is on the practical use of these techniques in domains such as computer vision, microscopy, health, energy and transportation.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors

  • 2021 Spotlight: Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis »
    Qi CHEN · Changjian Shui · Mario Marchand
  • 2022 : Metrics Reloaded »
    Annika Reinke · Lena Maier-Hein · Patrick Scholz · Minu D. Tizabi · Evangelia Christodoulou · Ben Glocker · Fabian Isensee · Jens Kleesiek · Michal Kozubek · Mauricio Reyes · Michael A. Riegler · Manuel Wiesenfarth · Michael Baumgartner · Matthias Eisenmann · Doreen Heckmann-Nötzel · A. Kavur · Tim Rädsch · Laura Acion · Michela Antonelli · Tal Arbel · Spyridon Bakas · Pete Bankhead · Arriel Benis · Florian Buettner · M. Jorge Cardoso · Veronika Cheplygina · Beth Cimini · Gary Collins · Keyvan Farahani · Luciana Ferrer · Adrian Galdran · Bram van Ginneken · Robert Haase · Daniel Hashimoto · Michael Hoffman · Merel Huisman · Pierre Jannin · Charles Kahn · Dagmar Kainmueller · Alexandros Karargyris · Bernhard Kainz · Alan Karthikesalingam · Hannes Kenngott · Florian Kofler · Annette Kopp-Schneider · Anna Kreshuk · Tahsin Kurc · Bennett Landman · Geert Litjens · Amin Madani · Klaus H. Maier-Hein · Anne Martel · Peter Mattson · Erik Meijering · Bjoern Menze · David Moher · Karel G.M. Moons · Henning Mueller · Brennan Nichyporuk · Felix Nickel · Jens Petersen · Nasir Rajpoot · Nicola Rieke · Julio Saez-Rodriguez · Clarisa Sanchez · Shravya Shetty · Maarten van Smeden · Carole Sudre · Ronald Summers · Abdel Aziz Taha · Sotirios Tsaftaris · Ben Ben Van Calster · Gaël Varoquaux · Paul Jäger
  • 2022 : Structured Priors for Disentangling Pathology and Anatomy in Patient Brain MRI »
    Anjun Hu · Jean-Pierre Falet · Changjian Shui · Brennan Nichyporuk · Sotirios Tsaftaris · Tal Arbel
  • 2022 Spotlight: Lightning Talks 2B-4 »
    Feiyi Xiao · Amrutha Saseendran · Kwangho Kim · Keyu Yan · Changjian Shui · Guangxi Li · Shikun Li · Edward Kennedy · Man Zhou · Gezheng Xu · Ruilin Ye · Xiaobo Xia · Junjie Tang · Kathrin Skubch · Stefan Falkner · Hansong Zhang · Jose Zubizarreta · Huaying Fang · Xuanqiang Zhao · Jie Huang · Qi CHEN · Yibing Zhan · Jiaqi Li · Xin Wang · Ruibin Xi · Feng Zhao · Margret Keuper · Charles Ling · Shiming Ge · Chengjun Xie · Tongliang Liu · Tal Arbel · Chongyi Li · Danfeng Hong · Boyu Wang · Christian Gagné
  • 2021 Poster: Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis »
    Qi CHEN · Changjian Shui · Mario Marchand
  • 2020 Poster: Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting »
    Jorge Mendez · Boyu Wang · Eric Eaton
  • 2019 Poster: Transfer Learning via Minimizing the Performance Gap Between Domains »
    Boyu Wang · Jorge Mendez · Mingbo Cai · Eric Eaton
  • 2018 : Is your machine learning method solving a real clinical problem? »
    Tal Arbel
  • 2018 Poster: Pelee: A Real-Time Object Detection System on Mobile Devices »
    Robert J. Wang · Tanner Bohn · Charles Ling