# Towards Fair Disentangled Online Learning for Changing Environments

arXiv: https://arxiv.org/abs/2306.01007 · HTML: https://mlsanity.com/paper/2306.01007/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 31 May 2023.

## Builds on (most cited first, 26 of 26)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [Domain Generalization for Object Recognition with Multi-task Autoencoders](https://mlsanity.com/paper/1508.07680/) (2015)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Online Meta-Learning](https://mlsanity.com/paper/1902.08438/) (2019)
- [Adaptive Online Learning in Dynamic Environments](https://mlsanity.com/paper/1810.10815/) (2018)
- [Strongly Adaptive Online Learning](https://mlsanity.com/paper/1502.07073/) (2015)
- [Model-Based Domain Generalization](https://mlsanity.com/paper/2102.11436/) (2021)
- [Online Convex Optimization with Stochastic Constraints](https://mlsanity.com/paper/1708.03741/) (2017)
- [Towards Principled Disentanglement for Domain Generalization](https://mlsanity.com/paper/2111.13839/) (2021)
- [Achieving Fairness in the Stochastic Multi-armed Bandit Problem](https://mlsanity.com/paper/1907.10516/) (2019)
- [Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient](https://mlsanity.com/paper/1605.04638/) (2016)
- [Adaptive Algorithms for Online Convex Optimization with Long-term Constraints](https://mlsanity.com/paper/1512.07422/) (2015)
- [Improved Strongly Adaptive Online Learning using Coin Betting](https://mlsanity.com/paper/1610.04578/) (2016)
- [Online convex optimization for cumulative constraints](https://mlsanity.com/paper/1802.06472/) (2018)
- [Improved Dynamic Regret for Non-degenerate Functions](https://mlsanity.com/paper/1608.03933/) (2016)
- [Regret and Cumulative Constraint Violation Analysis for Online Convex Optimization with Long Term Constraints](https://mlsanity.com/paper/2106.05135/) (2021)
- [Minimizing Dynamic Regret and Adaptive Regret Simultaneously](https://mlsanity.com/paper/2002.02085/) (2020)
- [Learning Fair Representation via Distributional Contrastive Disentanglement](https://mlsanity.com/paper/2206.08743/) (2022)
- [Rank-Based Multi-task Learning for Fair Regression](https://mlsanity.com/paper/2009.11405/) (2020)
- [Fairness-Aware Online Meta-learning](https://mlsanity.com/paper/2108.09435/) (2021)
- [Adaptive Fairness-Aware Online Meta-Learning for Changing Environments](https://mlsanity.com/paper/2205.11264/) (2022)
- [Unfairness Discovery and Prevention For Few-Shot Regression](https://mlsanity.com/paper/2009.11406/) (2020)

## Built on by (most cited first, 11 of 11)

- [Supervised Algorithmic Fairness in Distribution Shifts: A Survey](https://mlsanity.com/paper/2402.01327/) (2024)
- [Towards Counterfactual Fairness-aware Domain Generalization in Changing Environments](https://mlsanity.com/paper/2309.13005/) (2023)
- [Algorithmic Fairness Generalization under Covariate and Dependence Shifts Simultaneously](https://mlsanity.com/paper/2311.13816/) (2023)
- [Learning Fair Invariant Representations under Covariate and Correlation Shifts Simultaneously](https://mlsanity.com/paper/2408.09312/) (2024)
- [MADOD: Generalizing OOD Detection to Unseen Domains via G-Invariance Meta-Learning](https://mlsanity.com/paper/2411.02444/) (2024)
- [FADE: Towards Fairness-aware Generation for Domain Generalization via Classifier-Guided Score-based Diffusion Models](https://mlsanity.com/paper/2406.09495/) (2024)
- [MLDGG: Meta-Learning for Domain Generalization on Graphs](https://mlsanity.com/paper/2411.12913/) (2024)
- [Towards Effective Semantic OOD Detection in Unseen Domains: A Domain Generalization Perspective](https://mlsanity.com/paper/2309.10209/) (2023)
- [Enhancing Group Fairness in Online Settings Using Oblique Decision Forests](https://mlsanity.com/paper/2310.11401/) (2023)
- [FEED: Fairness-Enhanced Meta-Learning for Domain Generalization](https://mlsanity.com/paper/2411.01316/) (2024)
- [Feature-Space Semantic Invariance: Enhanced OOD Detection for Open-Set Domain Generalization](https://mlsanity.com/paper/2411.07392/) (2024)

## Abstract (arXiv)

In the problem of online learning for changing environments, data are sequentially received one after another over time, and their distribution assumptions may vary frequently. Although existing methods demonstrate the effectiveness of their learning algorithms by providing a tight bound on either dynamic regret or adaptive regret, most of them completely ignore learning with model fairness, defined as the statistical parity across different sub-population (e.g., race and gender). Another drawback is that when adapting to a new environment, an online learner needs to update model parameters with a global change, which is costly and inefficient. Inspired by the sparse mechanism shift hypothesis, we claim that changing environments in online learning can be attributed to partial changes in learned parameters that are specific to environments and the rest remain invariant to changing environments. To this end, in this paper, we propose a novel algorithm under the assumption that data collected at each time can be disentangled with two representations, an environment-invariant semantic factor and an environment-specific variation factor. The semantic factor is further used for fair prediction under a group fairness constraint. To evaluate the sequence of model parameters generated by the learner, a novel regret is proposed in which it takes a mixed form of dynamic and static regret metrics followed by a fairness-aware long-term constraint. The detailed analysis provides theoretical guarantees for loss regret and violation of cumulative fairness constraints. Empirical evaluations on real-world datasets demonstrate our proposed method sequentially outperforms baseline methods in model accuracy and fairness.