# Towards Learning an Unbiased Classifier from Biased Data via Conditional Adversarial Debiasing

arXiv: https://arxiv.org/abs/2103.06179 · HTML: https://mlsanity.com/paper/2103.06179/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 10 Mar 2021.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Learning Not to Learn: Training Deep Neural Networks with Biased Data](https://mlsanity.com/paper/1812.10352/) (2018)
- [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019)
- [Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation](https://mlsanity.com/paper/2007.09222/) (2020)
- [REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets](https://mlsanity.com/paper/2004.07999/) (2020)
- [Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings](https://mlsanity.com/paper/1809.02169/) (2018)
- [Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs](https://mlsanity.com/paper/1801.05453/) (2018)
- [Fair Kernel Learning](https://mlsanity.com/paper/1710.05578/) (2017)
- [Data Augmentation for Skin Lesion Analysis](https://mlsanity.com/paper/1809.01442/) (2018)
- [Kernel Dependence Regularizers and Gaussian Processes with Applications to Algorithmic Fairness](https://mlsanity.com/paper/1911.04322/) (2019)
- [Properties Of Winning Tickets On Skin Lesion Classification](https://mlsanity.com/paper/2008.12141/) (2020)

## Built on by (most cited first, 6 of 6)

- [The Pursuit of Fairness in Artificial Intelligence Models: A Survey](https://mlsanity.com/paper/2403.17333/) (2024)
- [Loss Balancing for Fair Supervised Learning](https://mlsanity.com/paper/2311.03714/) (2023)
- [Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspective](https://mlsanity.com/paper/2402.18607/) (2024)
- [PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection](https://mlsanity.com/paper/2507.08979/) (2025)
- [MLHOps: Machine Learning for Healthcare Operations](https://mlsanity.com/paper/2305.02474/) (2023)
- [The Pragmatic Frames of Spurious Correlations in Machine Learning: Interpreting How and Why They Matter](https://mlsanity.com/paper/2411.04696/) (2024)

## Abstract (arXiv)

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset, frequently caused by the co-occurrence of relevant features and irrelevant ones. To mitigate this issue, we require learning algorithms that prevent the propagation of bias from the dataset into the classifier. We present a novel adversarial debiasing method, which addresses a feature that is spuriously connected to the labels of training images but statistically independent of the labels for test images. Thus, the automatic identification of relevant features during training is perturbed by irrelevant features. This is the case in a wide range of bias-related problems for many computer vision tasks, such as automatic skin cancer detection or driver assistance. We argue by a mathematical proof that our approach is superior to existing techniques for the abovementioned bias. Our experiments show that our approach performs better than state-of-the-art techniques on a well-known benchmark dataset with real-world images of cats and dogs.