# Debiasify: Self-Distillation for Unsupervised Bias Mitigation

arXiv: https://arxiv.org/abs/2411.00711 · HTML: https://mlsanity.com/paper/2411.00711/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 32 of its 43 references that are in the map.
- First posted on arXiv 1 Nov 2024.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 30 of 32)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [The Pitfalls of Simplicity Bias in Neural Networks](https://mlsanity.com/paper/2006.07710/) (2020)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems](https://mlsanity.com/paper/2011.12945/) (2020)
- [Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Dataset](https://mlsanity.com/paper/2104.09957/) (2021)
- [What shapes feature representations? Exploring datasets, architectures, and training](https://mlsanity.com/paper/2006.12433/) (2020)
- [Learning Debiased Representation via Disentangled Feature Augmentation](https://mlsanity.com/paper/2107.01372/) (2021)
- [Discover and Cure: Concept-aware Mitigation of Spurious Correlation](https://mlsanity.com/paper/2305.00650/) (2023)
- [BiaSwap: Removing dataset bias with bias-tailored swapping augmentation](https://mlsanity.com/paper/2108.10008/) (2021)
- [MaskTune: Mitigating Spurious Correlations by Forcing to Explore](https://mlsanity.com/paper/2210.00055/) (2022)
- [Post-processing for Individual Fairness](https://mlsanity.com/paper/2110.13796/) (2021)
- [Fair Feature Distillation for Visual Recognition](https://mlsanity.com/paper/2106.04411/) (2021)
- [FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis](https://mlsanity.com/paper/2203.02110/) (2022)
- [Fair and Optimal Classification via Post-Processing](https://mlsanity.com/paper/2211.01528/) (2022)
- [Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline](https://mlsanity.com/paper/2106.06054/) (2021)
- [Unsupervised Learning of Debiased Representations with Pseudo-Attributes](https://mlsanity.com/paper/2108.02943/) (2021)
- [SelecMix: Debiased Learning by Contradicting-pair Sampling](https://mlsanity.com/paper/2211.02291/) (2022)
- [Overcoming Simplicity Bias in Deep Networks using a Feature Sieve](https://mlsanity.com/paper/2301.13293/) (2023)
- [NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization](https://mlsanity.com/paper/2109.02038/) (2021)
- [FairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learning](https://mlsanity.com/paper/2208.10013/) (2022)
- [BiasPruner: Debiased Continual Learning for Medical Image Classification](https://mlsanity.com/paper/2407.08609/) (2024)
- [Discover and Mitigate Multiple Biased Subgroups in Image Classifiers](https://mlsanity.com/paper/2403.12777/) (2024)
- [A Too-Good-to-be-True Prior to Reduce Shortcut Reliance](https://mlsanity.com/paper/2102.06406/) (2021)
- [Using Early Readouts to Mediate Featural Bias in Distillation](https://mlsanity.com/paper/2310.18590/) (2023)

## Abstract (arXiv)

Simplicity bias poses a significant challenge in neural networks, often leading models to favor simpler solutions and inadvertently learn decision rules influenced by spurious correlations. This results in biased models with diminished generalizability. While many current approaches depend on human supervision, obtaining annotations for various bias attributes is often impractical. To address this, we introduce Debiasify, a novel self-distillation approach that requires no prior knowledge about the nature of biases. Our method leverages a new distillation loss to transfer knowledge within the network, from deeper layers containing complex, highly-predictive features to shallower layers with simpler, attribute-conditioned features in an unsupervised manner. This enables Debiasify to learn robust, debiased representations that generalize effectively across diverse biases and datasets, improving both worst-group performance and overall accuracy. Extensive experiments on computer vision and medical imaging benchmarks demonstrate the effectiveness of our approach, significantly outperforming previous unsupervised debiasing methods (e.g., a 10.13% improvement in worst-group accuracy for Wavy Hair classification in CelebA) and achieving comparable or superior performance to supervised approaches. Our code is publicly available at the following link: Debiasify.