DISCO: Mitigating Bias in Deep Learning with Conditional DIStance COrrelation
Keywords: Causality, Counterfactual Invariance, Bias Mitigation, Causal Inference
TL;DR: A paper consisting of a theoretical analysis of counterfactual invariance using causal graphs, and a concrete practical solution to achieve invariance using conditional distance correlation.
Abstract: During prediction tasks, models can use any signal they receive to come up with
the final answer - including signals that are causally irrelevant. When predicting
objects from images, for example, the lighting conditions could be correlated to
different targets through selection bias, and an oblivious model might use these
signals as shortcuts to discern between various objects. A predictor that uses
lighting conditions instead of real object-specific details is obviously undesirable.
To address this challenge, we introduce a standard anti-causal prediction model
(SAM) that creates a causal framework for analyzing the information pathways
influencing our predictor in anti-causal settings. We demonstrate that a classifier
satisfying a specific conditional independence criterion will focus solely on the
direct causal path from label to image, being counterfactually invariant to the
remaining variables. Finally, we propose DISCO, a novel regularization strategy
that uses conditional distance correlation to optimize for conditional independence
in regression tasks. We can show that DISCO achieves competitive results in
different bias mitigation experiments, deeming it a valid alternative to classical
kernel-based methods.
Primary Area: causal reasoning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6523
Loading