# Mind the Graph When Balancing Data for Fairness or Robustness

arXiv: https://arxiv.org/abs/2406.17433 · HTML: https://mlsanity.com/paper/2406.17433/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 82 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Builds on (most cited first, 30 of 44)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [An Investigation of Why Overparameterization Exacerbates Spurious Correlations](https://mlsanity.com/paper/2005.04345/) (2020)
- [What is the Effect of Importance Weighting in Deep Learning?](https://mlsanity.com/paper/1812.03372/) (2018)
- [Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach](https://mlsanity.com/paper/1610.03425/) (2016)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [Simple data balancing achieves competitive worst-group-accuracy](https://mlsanity.com/paper/2110.14503/) (2021)
- [Characterising Bias in Compressed Models](https://mlsanity.com/paper/2010.03058/) (2020)
- [Reading Race: AI Recognises Patient's Racial Identity In Medical Images](https://mlsanity.com/paper/2107.10356/) (2021)
- [Identifying and Correcting Label Bias in Machine Learning](https://mlsanity.com/paper/1901.04966/) (2019)
- [Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions](https://mlsanity.com/paper/1707.06422/) (2017)
- [Discover and Cure: Concept-aware Mitigation of Spurious Correlation](https://mlsanity.com/paper/2305.00650/) (2023)
- [Causally motivated Shortcut Removal Using Auxiliary Labels](https://mlsanity.com/paper/2105.06422/) (2021)
- [Towards Last-layer Retraining for Group Robustness with Fewer Annotations](https://mlsanity.com/paper/2309.08534/) (2023)
- [Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing](https://mlsanity.com/paper/2207.10384/) (2022)
- [A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?](https://mlsanity.com/paper/2112.00639/) (2021)
- [Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning](https://mlsanity.com/paper/2304.03916/) (2023)
- [Fair Bayesian Optimization](https://mlsanity.com/paper/2006.05109/) (2020)
- [Diagnosing failures of fairness transfer across distribution shift in real-world medical settings](https://mlsanity.com/paper/2202.01034/) (2022)
- [Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations](https://mlsanity.com/paper/2107.00520/) (2021)
- [Fair and Diverse DPP-based Data Summarization](https://mlsanity.com/paper/1802.04023/) (2018)
- [CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?](https://mlsanity.com/paper/2403.04547/) (2024)

## Built on by (most cited first, 9 of 9)

- [Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models](https://mlsanity.com/paper/2510.03721/) (2025)
- [Subgroups Matter for Robust Bias Mitigation](https://mlsanity.com/paper/2505.21363/) (2025)
- [Does Weak-to-strong Generalization Happen under Spurious Correlations?](https://mlsanity.com/paper/2509.24005/) (2025)
- [Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs](https://mlsanity.com/paper/2602.03895/) (2026)
- [Structure-agnostic Causal Representation Learning](https://mlsanity.com/paper/2610.00968/) (2026)
- [Causal Fine-Tuning under Latent Confounded Shift](https://mlsanity.com/paper/2410.14375/) (2024)
- [A Critical Review of Predominant Bias in Neural Networks](https://mlsanity.com/paper/2502.11031/) (2025)
- [Representation Invariance and Allocation: When Subgroup Balance Matters](https://mlsanity.com/paper/2512.09496/) (2025)
- [DeconDTN-Toolkit: A Library for Evaluation and Enhancement of Robustness to Provenance Shift](https://mlsanity.com/paper/2605.11237/) (2026)

## Abstract (arXiv)

Failures of fairness or robustness in machine learning predictive settings can be due to undesired dependencies between covariates, outcomes and auxiliary factors of variation. A common strategy to mitigate these failures is data balancing, which attempts to remove those undesired dependencies. In this work, we define conditions on the training distribution for data balancing to lead to fair or robust models. Our results display that, in many cases, the balanced distribution does not correspond to selectively removing the undesired dependencies in a causal graph of the task, leading to multiple failure modes and even interference with other mitigation techniques such as regularization. Overall, our results highlight the importance of taking the causal graph into account before performing data balancing.