Pith. sign in

REVIEW 1 cited by

Causally motivated Shortcut Removal Using Auxiliary Labels

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2105.06422 v3 pith:2R2XAXW7 submitted 2021-05-13 cs.LG

classification cs.LG
keywords shortcutrobusttrainingapproachauxiliaryavailablecausalcausally
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Shortcut learning, in which models make use of easy-to-represent but unstable associations, is a major failure mode for robust machine learning. We study a flexible, causally-motivated approach to training robust predictors by discouraging the use of specific shortcuts, focusing on a common setting where a robust predictor could achieve optimal \emph{iid} generalization in principle, but is overshadowed by a shortcut predictor in practice. Our approach uses auxiliary labels, typically available at training time, to enforce conditional independences implied by the causal graph. We show both theoretically and empirically that causally-motivated regularization schemes (a) lead to more robust estimators that generalize well under distribution shift, and (b) have better finite sample efficiency compared to usual regularization schemes, even when no shortcut is present. Our analysis highlights important theoretical properties of training techniques commonly used in the causal inference, fairness, and disentanglement literatures. Our code is available at https://github.com/mymakar/causally_motivated_shortcut_removal

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 8 citations worldwide. Full citation record

  1. Revisiting Performance Claims for Chest X-Ray Models Using Clinical Context

    cs.LG 2025-09 conditional novelty 6.0 of 10

    Chest X-ray models' apparent accuracy drops significantly when evaluated on cases matched to remove clinical context from prior notes, suggesting much of their performance relies on context rather than image evidence.

Pith tools