DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation
Not on the map. Why?
Abstract (arXiv)
Dataset bias often leads deep learning models to exploit spurious correlations instead of task-relevant signals. We introduce the Standard Anti-Causal Model (SAM), a unifying causal framework that characterizes bias mechanisms and yields a conditional independence criterion for causal stability. Building on this theory, we propose DISCOm and sDISCO, efficient and scalable estimators of conditional distance correlation that enable independence regularization in gradient-based models. Across six diverse datasets, our methods consistently outperform or are competitive in existing observed bias mitigation approaches, while requiring fewer hyperparameters and scaling seamlessly to multi-bias scenarios. This work bridges causal theory and practical deep learning, providing both a principled foundation and effective tools for robust prediction. Source Code: https://github.com/yakamoz5/DISCO.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 84 references that are in the map. First posted on arXiv 13 Jun 2025.
Builds on
36 of 84 references.
References · 36
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2015Domain-Adversarial Training of Neural Networkscited by 3,044
- 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
- 2020Shortcut Learning in Deep Neural Networkscited by 1,969
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
- 2019Invariant Risk Minimizationcited by 1,854
- 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
- 2017Counterfactual Fairnesscited by 804
- 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 410
- 2013Direct and Indirect Effectscited by 280
- 2020Domain Generalization using Causal Matchingcited by 225
- 2017Avoiding Discrimination through Causal Reasoningcited by 194
24 more
- 2018Path-Specific Counterfactual Fairnesscited by 181
- 2016Identifying Causal Effects With Proxy Variables of an Unmeasured Confoundercited by 139
- 2020An Introduction to Proximal Causal Learningcited by 95
- 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
- 2020A Measure-Theoretic Approach to Kernel Conditional Mean Embeddingscited by 86
- 2021Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Testscited by 77
- 2022Probable Domain Generalization via Quantile Risk Minimizationcited by 66
- 2021Causally motivated Shortcut Removal Using Auxiliary Labelscited by 55
- 2024Vision-and-Language Navigation via Causal Learningcited by 51
- 2022Causal Fairness Analysiscited by 43
- 2021Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlationscited by 41
- 2021Nested Counterfactual Identification from Arbitrary Surrogate Experimentscited by 38
- 2022Invariant and Transportable Representations for Anti-Causal Domain Shiftscited by 37
- 2022Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalizationcited by 34
- 2013Partial Distance Correlation with Methods for Dissimilaritiescited by 20
- 2022Deep Learning of Causal Structures in High Dimensionscited by 20
- 2022Efficient Conditionally Invariant Representation Learningcited by 19
- 2020Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networkscited by 16
- 2022Deep Learning Methods for Proximal Inference via Maximum Moment Restrictioncited by 14
- 2023Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanismscited by 14
- 2025A Practical Introduction to Kernel Discrepancies: MMD, HSIC & KSDcited by 13
- 2023No Fair Lunch: A Causal Perspective on Dataset Bias in Machine Learning for Medical Imagingcited by 11
- 2022Learning Counterfactually Invariant Predictorscited by 10
- 2022Fairness and robustness in anti-causal predictioncited by 10
Built on by
Not cited yet.