DISCO: Mitigating Bias in Deep Learning With Conditional Distance Correlation

MCML Authors

Emre Kavak

→ Group Christian Wachinger
 Artificial Intelligence in Medical Imaging

Tom Nuno Wolf

→ Group Christian Wachinger
 Artificial Intelligence in Medical Imaging

Christian Wachinger

Prof. Dr.

Core PI

Artificial Intelligence in Medical Imaging

Abstract

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 DISCO 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.

inproceedings KWW+26

---

ICML 2026

43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. Spotlight Presentation. To be published. Preprint available.

---

Authors

E. Kavak • T. N. Wolf • C. Wachinger

---

Links

URL GitHub

---

Research Area

 C1 | Medicine