# Balancing Fairness and Robustness via Partial Invariance

arXiv: https://arxiv.org/abs/2112.09346 · HTML: https://mlsanity.com/paper/2112.09346/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 17 Dec 2021.

## Builds on (most cited first, 23 of 23)

- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Gauge Equivariant Convolutional Networks and the Icosahedral CNN](https://mlsanity.com/paper/1902.04615/) (2019)
- [The Risks of Invariant Risk Minimization](https://mlsanity.com/paper/2010.05761/) (2020)
- [Domain Generalization using Causal Matching](https://mlsanity.com/paper/2006.07500/) (2020)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [Invariant Risk Minimization Games](https://mlsanity.com/paper/2002.04692/) (2020)
- [Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach](https://mlsanity.com/paper/1610.03425/) (2016)
- [Deep Learning for Hate Speech Detection in Tweets](https://mlsanity.com/paper/1706.00188/) (2017)
- [Domain Generalization via Conditional Invariant Representation](https://mlsanity.com/paper/1807.08479/) (2018)
- [Invariant Causal Prediction for Nonlinear Models](https://mlsanity.com/paper/1706.08576/) (2017)
- [Does Invariant Risk Minimization Capture Invariance?](https://mlsanity.com/paper/2101.01134/) (2021)
- [Building machines that adapt and compute like brains](https://mlsanity.com/paper/1711.04203/) (2017)
- [Empirical or Invariant Risk Minimization? A Sample Complexity Perspective](https://mlsanity.com/paper/2010.16412/) (2020)
- [Hate Speech Detection: A Solved Problem? The Challenging Case of Long Tail on Twitter](https://mlsanity.com/paper/1803.03662/) (2018)
- [Fairness and Robustness in Invariant Learning: A Case Study in Toxicity Classification](https://mlsanity.com/paper/2011.06485/) (2020)
- [Leveraging cross-platform data to improve automated hate speech detection](https://mlsanity.com/paper/2102.04895/) (2021)
- [Quantization Games on Social Networks and Language Evolution](https://mlsanity.com/paper/2006.00584/) (2020)

## Built on by (most cited first, 1 of 1)

- [Position: Categorical Deep Learning is an Algebraic Theory of All Architectures](https://mlsanity.com/paper/2402.15332/) (2024)

## Abstract (arXiv)

The Invariant Risk Minimization (IRM) framework aims to learn invariant features from a set of environments for solving the out-of-distribution (OOD) generalization problem. The underlying assumption is that the causal components of the data generating distributions remain constant across the environments or alternately, the data "overlaps" across environments to find meaningful invariant features. Consequently, when the "overlap" assumption does not hold, the set of truly invariant features may not be sufficient for optimal prediction performance. Such cases arise naturally in networked settings and hierarchical data-generating models, wherein the IRM performance becomes suboptimal. To mitigate this failure case, we argue for a partial invariance framework. The key idea is to introduce flexibility into the IRM framework by partitioning the environments based on hierarchical differences, while enforcing invariance locally within the partitions. We motivate this framework in classification settings with causal distribution shifts across environments. Our results show the capability of the partial invariant risk minimization to alleviate the trade-off between fairness and risk in certain settings.