# Data augmentation and explainability for bias discovery and mitigation in deep learning arXiv: https://arxiv.org/abs/2308.09464 ยท HTML: https://mlsanity.com/paper/2308.09464/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Builds on 28 of its 218 references that are in the map. - First posted on arXiv 18 Aug 2023. ## Builds on (most cited first, 28 of 28) - [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019) - [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014) - [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019) - [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017) - [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019) - [WebVision Database: Visual Learning and Understanding from Web Data](https://mlsanity.com/paper/1708.02862/) (2017) - [Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey](https://mlsanity.com/paper/2006.11371/) (2020) - [Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems](https://mlsanity.com/paper/1805.04508/) (2018) - [BCN20000: Dermoscopic Lesions in the Wild](https://mlsanity.com/paper/1908.02288/) (2019) - [A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle](https://mlsanity.com/paper/1901.10002/) (2019) - [Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks](https://mlsanity.com/paper/1602.03616/) (2016) - [Fast Patch-based Style Transfer of Arbitrary Style](https://mlsanity.com/paper/1612.04337/) (2016) - [Regularization for Deep Learning: A Taxonomy](https://mlsanity.com/paper/1710.10686/) (2017) - [The Unfairness of Popularity Bias in Recommendation](https://mlsanity.com/paper/1907.13286/) (2019) - [Gender Bias in Masked Language Models for Multiple Languages](https://mlsanity.com/paper/2205.00551/) (2022) - [Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values](https://mlsanity.com/paper/1810.03307/) (2018) - [A statistical framework for fair predictive algorithms](https://mlsanity.com/paper/1610.08077/) (2016) - [TACO: Trash Annotations in Context for Litter Detection](https://mlsanity.com/paper/2003.06975/) (2020) - [Spatial Frequency Bias in Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/2010.01473/) (2020) - [Global Aggregations of Local Explanations for Black Box models](https://mlsanity.com/paper/1907.03039/) (2019) - [Identifying Melanoma Images using EfficientNet Ensemble: Winning Solution to the SIIM-ISIC Melanoma Classification Challenge](https://mlsanity.com/paper/2010.05351/) (2020) - [Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud](https://mlsanity.com/paper/2109.03285/) (2021) - [A study of data and label shift in the LIME framework](https://mlsanity.com/paper/1910.14421/) (2019) - [Bias Amplification in Artificial Intelligence Systems](https://mlsanity.com/paper/1809.07842/) (2018) - [IFBiD: Inference-Free Bias Detection](https://mlsanity.com/paper/2109.04374/) (2021) - [Quality Metrics for Transparent Machine Learning With and Without Humans In the Loop Are Not Correlated](https://mlsanity.com/paper/2107.02033/) (2021) - [Bias in Machine Learning -- What is it Good for?](https://mlsanity.com/paper/2004.00686/) (2020) - [Can collider bias fully explain the obesity paradox?](https://mlsanity.com/paper/1612.06547/) (2016) ## Built on by (most cited first, 2 of 2) - [Explanatory Debiasing: Involving Domain Experts in the Data Generation Process to Mitigate Representation Bias in AI Systems](https://mlsanity.com/paper/2501.01441/) (2024) - [A survey on bias in machine learning research](https://mlsanity.com/paper/2308.11254/) (2023) ## Abstract (arXiv) This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data and models, with a particular focus on bias in machine learning pipelines. The next chapter outlines a taxonomy and methods of Explainable AI as a way to justify predictions and control and improve the model. Then, as an example of a laborious manual data inspection and bias discovery process, a skin lesion dataset is manually examined. A Global Explanation for the Bias Identification method is proposed as an alternative semi-automatic approach to manual data exploration for discovering potential biases in data. Relevant numerical methods and metrics are discussed for assessing the effects of the identified biases on the model. Whereas identifying errors and bias is critical, improving the model and reducing the number of flaws in the future is an absolute priority. Hence, the second part of the thesis focuses on mitigating the influence of bias on ML models. Three approaches are proposed and discussed: Style Transfer Data Augmentation, Targeted Data Augmentations, and Attribution Feedback. Style Transfer Data Augmentation aims to address shape and texture bias by merging a style of a malignant lesion with a conflicting shape of a benign one. Targeted Data Augmentations randomly insert possible biases into all images in the dataset during the training, as a way to make the process random and, thus, destroy spurious correlations. Lastly, Attribution Feedback is used to fine-tune the model to improve its accuracy by eliminating obvious mistakes and teaching it to ignore insignificant input parts via an attribution loss. The goal of these approaches is to reduce the influence of bias on machine learning models, rather than eliminate it entirely.