Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
skip to main content
10.1145/3534678.3539420acmconferencesArticle/Chapter ViewAbstractPublication PageskddConference Proceedingsconference-collections
research-article
Open access

Adaptive Fairness-Aware Online Meta-Learning for Changing Environments

Published: 14 August 2022 Publication History

Abstract

The fairness-aware online learning framework has arisen as a powerful tool for the continual lifelong learning setting. The goal for the learner is to sequentially learn new tasks where they come one after another over time and the learner ensures the statistic parity of the new coming task across different protected sub-populations (e.g. race and gender). A major drawback of existing methods is that they make heavy use of the i.i.d assumption for data and hence provide static regret analysis for the framework. However, low static regret cannot imply a good performance in changing environments where tasks are sampled from heterogeneous distributions. To address the fairness-aware online learning problem in changing environments, in this paper, we first construct a novel regret metric FairSAR by adding long-term fairness constraints onto a strongly adapted loss regret. Furthermore, to determine a good model parameter at each round, we propose a novel adaptive fairness-aware online meta-learning algorithm, namely FairSAOML, which is able to adapt to changing environments in both bias control and model precision. The problem is formulated in the form of a bi-level convex-concave optimization with respect to the model's primal and dual parameters that are associated with the model's accuracy and fairness, respectively. The theoretic analysis provides sub-linear upper bounds for both loss regret and violation of cumulative fairness constraints. Our experimental evaluation on different real-world datasets with settings of changing environments suggests that the proposed FairSAOML significantly outperforms alternatives based on the best prior online learning approaches.

References

[1]
Dan Biddle. 2005. Adverse Impact and Test Validation: A Practitioner's Guide to Valid and Defensible Employment Testing. Gower (2005).
[2]
Nicolò Cesa-Bianchi and Gábor Lugosi. 2006. Prediction, Learning, and Games. Cambridge University Press (2006).
[3]
Amit Daniely, Alon Gonen, and Shai Shalev-Shwartz. 2015a. Strongly Adaptive Online Learning. In ICML.
[4]
Amit Daniely, Alon Gonen, and Shai Shalev-Shwartz. 2015b. Strongly Adaptive Online Learning. In ICML.
[5]
Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Rich Zemel. 2011. Fairness Through Awareness. CoRR (2011).
[6]
Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. ICML (2017).
[7]
Chelsea Finn, Aravind Rajeswaran, Sham Kakade, and Sergey Levine. 2019. Online Meta-Learning. ICML (2019).
[8]
András Gyorgy, Tamás Linder, and Gábor Lugosi. 2012. Efficient tracking of large classes of experts. IEEE Transactions on Information Theory (2012).
[9]
Moritz Hardt, Eric Price, and Nathan Srebro. 2016. Equality of opportunity in supervised learning. NeurIPS (2016).
[10]
Elad Hazan and Edgar Minasyan. 2020. Faster Projection-free Online Learning. In Proceedings of Thirty Third Conference on Learning Theory.
[11]
Elad Hazan and C. Seshadhri. 2007. Adaptive Algorithms for Online Decision Problems. Electronic Colloquium on Computational Complexity (ECCC) (2007).
[12]
Rodolphe Jenatton, Jim Huang, and Cedric Archambeau. 2016. Adaptive Algorithms for Online Convex Optimization with Long-term Constraints. ICML (2016).
[13]
Kwang-Sung Jun, Francesco Orabona, Stephen Wright, and Rebecca Willett. 2017. Improved Strongly Adaptive Online Learning using Coin Betting. In AISTATS.
[14]
Pang Wei Koh, Shiori Sagawa, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, Tony Lee, Etienne David, Ian Stavness, Wei Guo, Berton Earnshaw, Imran Haque, Sara M Beery, Jure Leskovec, Anshul Kundaje, Emma Pierson, Sergey Levine, Chelsea Finn, and Percy Liang. 2021. WILDS: A Benchmark of in-the-Wild Distribution Shifts. In ICML.
[15]
Michael Lohaus, Michael Perrot, and Ulrike Von Luxburg. 2020. Too Relaxed to Be Fair. In ICML.
[16]
Haipeng Luo and Robert E Schapire. 2015. Achieving all with no parameters: Adanormalhedge. In Conference on Learning Theory. PMLR, 1286--1304.
[17]
Mehrdad Mahdavi, Rong Jin, and Tianbao Yang. 2012. Trading regret for efficiency: online convex optimization with long term constraints. JMLR (2012).
[18]
Jennifer Miller. 2020. Is an Algorithm Less Racist Than a Loan Officer? www.nytimes.com/2020/09/18/business/digital-mortgages.html (2020).
[19]
Yuanyu Wan, Bo Xue, and Lijun Zhang. 2021. Projection-free Online Learning in Dynamic Environments. AAAI (2021).
[20]
Zhuoyi Wang, Yuqiao Chen, Chen Zhao, Yu Lin, Xujiang Zhao, Hemeng Tao, Yigong Wang, and Latifur Khan. 2021. CLEAR: Contrastive-Prototype Learning with Drift Estimation for Resource Constrained Stream Mining. In WWW.
[21]
Yongkai Wu, Lu Zhang, and Xintao Wu. 2019. On Convexity and Bounds of Fairness-aware Classification. WWW.
[22]
Jiahao Xie, Zebang Shen, Chao Zhang, Boyu Wang, and Hui Qian. 2020. Efficient projection-free online methods with stochastic recursive gradient. In AAAI.
[23]
Jianjun Yuan and Andrew Lamperski. 2018. Online convex optimization for cumulative constraints. NeurIPS (2018).
[24]
Lijun Zhang, Shiyin Lu, and Tianbao Yang. 2020. Minimizing Dynamic Regret and Adaptive Regret Simultaneously. AISTATS (2020).
[25]
Lijun Zhang, Shiyin Lu, and Zhi-Hua Zhou. 2018. Adaptive Online Learning in Dynamic Environments, In International Conference on Neural Information Processing Systems. NeurIPS 2018.
[26]
Chen Zhao and Feng Chen. 2019. Rank-Based Multi-task Learning For Fair Regression. IEEE International Conference on Data Mining (ICDM) (2019).
[27]
Chen Zhao and Feng Chen. 2020. Unfairness Discovery and Prevention For Few-Shot Regression. ICKG (2020).
[28]
Chen Zhao, Feng Chen, and Bhavani Thuraisingham. 2021. Fairness-Aware Online Meta-learning. ACM SIGKDD (2021).
[29]
Martin Zinkevich. 2003. Online Convex Programming and Generalized Infinitesimal Gradient Ascent. ICML (2003).

Cited By

View all
  • (2024)Supervised algorithmic fairness in distribution shiftsProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence10.24963/ijcai.2024/909(8225-8233)Online publication date: 3-Aug-2024
  • (2024)Towards counterfactual fairness-aware domain generalization in changing environmentsProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence10.24963/ijcai.2024/504(4560-4568)Online publication date: 3-Aug-2024
  • (2024)Dynamic Environment Responsive Online Meta-Learning with Fairness AwarenessACM Transactions on Knowledge Discovery from Data10.1145/364868418:6(1-23)Online publication date: 29-Apr-2024
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
August 2022
5033 pages
ISBN:9781450393850
DOI:10.1145/3534678
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 14 August 2022

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. adaption
  2. changing environment
  3. fairness
  4. online meta-learning

Qualifiers

  • Research-article

Conference

KDD '22
Sponsor:

Acceptance Rates

Overall Acceptance Rate 1,133 of 8,635 submissions, 13%

Upcoming Conference

KDD '25

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)316
  • Downloads (Last 6 weeks)35
Reflects downloads up to 26 Jan 2025

Other Metrics

Citations

Cited By

View all
  • (2024)Supervised algorithmic fairness in distribution shiftsProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence10.24963/ijcai.2024/909(8225-8233)Online publication date: 3-Aug-2024
  • (2024)Towards counterfactual fairness-aware domain generalization in changing environmentsProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence10.24963/ijcai.2024/504(4560-4568)Online publication date: 3-Aug-2024
  • (2024)Dynamic Environment Responsive Online Meta-Learning with Fairness AwarenessACM Transactions on Knowledge Discovery from Data10.1145/364868418:6(1-23)Online publication date: 29-Apr-2024
  • (2024)Algorithmic Fairness Generalization under Covariate and Dependence Shifts SimultaneouslyProceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining10.1145/3637528.3671909(4419-4430)Online publication date: 25-Aug-2024
  • (2024)3rd Workshop on Ethical Artificial Intelligence: Methods and Applications (EAI)Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining10.1145/3637528.3671482(6751-6752)Online publication date: 25-Aug-2024
  • (2024)Learning Fair Invariant Representations under Covariate and Correlation Shifts SimultaneouslyProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3679727(1174-1183)Online publication date: 21-Oct-2024
  • (2024)Online Resource Allocation for Edge Intelligence with Colocated Model Retraining and InferenceIEEE INFOCOM 2024 - IEEE Conference on Computer Communications10.1109/INFOCOM52122.2024.10621206(1900-1909)Online publication date: 20-May-2024
  • (2024)FEED: Fairness-Enhanced Meta-Learning for Domain Generalization2024 IEEE International Conference on Big Data (BigData)10.1109/BigData62323.2024.10825892(949-958)Online publication date: 15-Dec-2024
  • (2024)MADOD: Generalizing OOD Detection to Unseen Domains via G-Invariance Meta-Learning2024 IEEE International Conference on Big Data (BigData)10.1109/BigData62323.2024.10825441(1134-1143)Online publication date: 15-Dec-2024
  • (2023)Towards Fair Disentangled Online Learning for Changing EnvironmentsProceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining10.1145/3580305.3599523(3480-3491)Online publication date: 6-Aug-2023
  • Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media