Papers › Causally motivated Shortcut Removal Using Auxiliary Labels

Causally motivated Shortcut Removal Using Auxiliary Labels

13 May 2021arXiv:2105.06422archive 2025-07-28

Maggie Makar, Ben Packer, Dan Moldovan, Davis Blalock, Yoni Halpern, Alexander D'Amour

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

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2105.06422")

Code

Syntology Ran 0 of 11 code samples harvested from 1 repository linked to this paper; 11 have no recorded run.

By repository: official repository: 11 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mymakar/causally_motivated_shortcut_removal officialmentioned in papertfApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested; 0 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

11unverified

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from mymakar/causally_motivated_shortcut_removal. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

compute_pred_loss mymakar/causally_motivated_shortcut_removal/shared/evaluation_metrics.py official repository unverified Apache-2.0 (permissive) · f5d713c3ef15f625 · report
create_architecture mymakar/causally_motivated_shortcut_removal/shared/architectures.py official repository unverified Apache-2.0 (permissive) · ef3ba340df457610 · report
decode_number mymakar/causally_motivated_shortcut_removal/chexpert/data_builder.py official repository unverified Apache-2.0 (permissive) · bccc96ebed03600f · report
extract_weights mymakar/causally_motivated_shortcut_removal/shared/train_utils.py official repository unverified Apache-2.0 (permissive) · 30b2e469555255e7 · report
flatten_dict mymakar/causally_motivated_shortcut_removal/shared/train_utils.py official repository unverified Apache-2.0 (permissive) · 3e2e16445f6f92e6 · report
get_last_saved_model mymakar/causally_motivated_shortcut_removal/shared/get_sigma.py official repository unverified Apache-2.0 (permissive) · 36df5a80dc755620 · report
get_optimal_model_classic mymakar/causally_motivated_shortcut_removal/shared/cross_validation.py official repository unverified Apache-2.0 (permissive) · 031fc88b30375099 · report
map_to_image_label mymakar/causally_motivated_shortcut_removal/chexpert/data_builder.py official repository unverified Apache-2.0 (permissive) · 12b5a06366dc915e · report
read_decode_jpg mymakar/causally_motivated_shortcut_removal/chexpert/data_builder.py official repository unverified Apache-2.0 (permissive) · 1406483012c2b867 · report
read_decode_png mymakar/causally_motivated_shortcut_removal/waterbirds/data_builder.py official repository unverified Apache-2.0 (permissive) · 570c66778860579a · report
reshape_results mymakar/causally_motivated_shortcut_removal/shared/cross_validation.py official repository unverified Apache-2.0 (permissive) · 3715e0dc12e4f657 · report

Tasks

Causal InferenceDisentanglementFairness

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections