Papers › Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness

Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness

9 Oct 2023arXiv:2310.06161archive 2025-07-28

Bhavya Vasudeva, Kameron Shahabi, Vatsal Sharan

Neural networks (NNs) are known to exhibit simplicity bias where they tend to prefer learning 'simple' features over more 'complex' ones, even when the latter may be more informative. Simplicity bias can lead to the model making biased predictions which have poor out-of-distribution (OOD) generalization. To address this, we propose a framework that encourages the model to use a more diverse set of features to make predictions. We first train a simple model, and then regularize the conditional mutual information with respect to it to obtain the final model. We demonstrate the effectiveness of this framework in various problem settings and real-world applications, showing that it effectively addresses simplicity bias and leads to more features being used, enhances OOD generalization, and improves subgroup robustness and fairness. We complement these results with theoretical analyses of the effect of the regularization and its OOD generalization properties.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 10 ran (5 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

estija/cmid officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 10 ran (5 instrument-failed) · 5 unverified 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

15 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
2ran; the contract check could not run
5ran
5unverified

Licence: 1 of the 15 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from estija/cmid. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

estija/cmid official repository 15 samples, 10 ran (5 instrument-failed) · 5 unverified
acc_and_f1 in 39 papers utils_glue.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) here; the stored copy is pointer only · cac113ca87b9d9f3 · report fixture: signature preds:ndarray/1/int, labels:ndarray/1/int · returned dict · level recorded 2026-09-22
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
utils.py ran; the contract check could not run (RAISES) MIT (permissive) · 621de5dd9c62c06d · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-25
convert_examples_to_features in 134 papers utils_glue.py ran · our draft was wrong MIT (permissive) · c4c16e96906f44c1 · report fixture: signature examples:list/1/Example, label_list:list/1/str, max_seq_length:int/0/int, tokenizer:SimpleTokenizer/0/?, output_mode:str/0/str, cls_token_at_end:bool/0/bool, cls_token:str/0/str, cls_token_segment_id:int/0/int, sep_token:str/0/str, sep_token_extra:bool/0/bool, pad_on_left:bool/0/bool, pad_token:int/0/int, pad_token_segment_id:int/0/int, sequence_a_segment_id:int/0/int, sequence_b_segment_id:int/0/int, mask_padding_with_zero:bool/0/bool · returned list · level recorded 2026-09-25
get_accs_for_epoch_across_batches in 5 papers analysis_utils.py ran · our draft was wrong MIT (permissive) · 381380e09fd105f8 · report fixture: signature df:DataFrame/0/?, epoch:int/0/int · returned tuple · level recorded 2026-09-25
get_balanced_data utils.py ran MIT (permissive) · d6fd8295f565dec5 · report fixture: signature train_data:list/1/tuple, dim:int/0/int · returned list · level recorded 2026-09-24
get_balanced_data_gen utils.py ran MIT (permissive) · 3c6b0889ccefaeda · report fixture: signature train_data:list/1/tuple, dim:int/0/int, args:Args/0/? · returned list · level recorded 2026-09-24
getbinvals cmi.py ran MIT (permissive) · f605c61af29ad962 · report fixture: signature M:Tensor/2/float, cen_arr:Tensor/1/float, Xv:Tensor/0/float, Yv:Tensor/0/float, device:device/0/?, sig:float/0/float · returned Tensor · level recorded 2026-09-24
kernel_val cmi.py ran fingerprinted MIT (permissive) · b2d727e185d69fb0 · report fixture: signature x:Tensor/2/float, mu:Tensor/2/float, sig:float/0/float · returned Tensor · level recorded 2026-09-24
sanitize_df in 5 papers analysis_utils.py ran · our draft was wrong MIT (permissive) · 8a66892616008c7f · report fixture: signature df:DataFrame/0/? · returned DataFrame · level recorded 2026-09-25
validate in 313 papers camelyon/camelyon.py ran MIT (permissive) · d97abd07bae67ef4 · report fixture: signature val_loader:list/1/tuple, model:callable/0/?, criterion:callable/0/?, dataset:MinimalDataset/0/? · returned dict · level recorded 2026-09-24
combine_and_mask in 5 papers dataset_scripts/dataset_utils.py unverified MIT (permissive) · fe49a67591e2b166 · report
crop_and_resize in 11 papers dataset_scripts/dataset_utils.py unverified MIT (permissive) · e2f8b1a98dec9723 · report
est_IMYL cmi.py unverified MIT (permissive) · 8c45aa24af923432 · report
load_log in 9 papers analysis_utils.py unverified MIT (permissive) · 10e220982fed5f01 · report
simple_accuracy in 66 papers utils_glue.py unverified MIT (permissive) · 3c241ecfe3749a6d · report

Tasks

Fairness

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