Papers › Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions

Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions

10 Mar 2025arXiv:2503.07315archive 2025-07-28

Rui Qiao, Zhaoxuan Wu, Jingtan Wang, Pang Wei Koh, Bryan Kian Hsiang Low

Machine learning models often have uneven performance among subpopulations (a.k.a., groups) in the data distributions. This poses a significant challenge for the models to generalize when the proportions of the groups shift during deployment. To improve robustness to such shifts, existing approaches have developed strategies that train models or perform hyperparameter tuning using the group-labeled data to minimize the worst-case loss over groups. However, a non-trivial amount of high-quality labels is often required to obtain noticeable improvements. Given the costliness of the labels, we propose to adopt a different paradigm to enhance group label efficiency: utilizing the group-labeled data as a target set to optimize the weights of other group-unlabeled data. We introduce Group-robust Sample Reweighting (GSR), a two-stage approach that first learns the representations from group-unlabeled data, and then tinkers the model by iteratively retraining its last layer on the reweighted data using influence functions. Our GSR is theoretically sound, practically lightweight, and effective in improving the robustness to subpopulation shifts. In particular, GSR outperforms the previous state-of-the-art approaches that require the same amount or even more group labels.

PaperPDFCodeCode Syntology ranMethod as code

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.

Syntology holds a reference implementation of Group-robust Sample Reweighting (GSR), generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Group-robust Sample Reweighting (GSR)') (how to connect); the free check have('2503.07315') needs no token.

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

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 4 ran (2 with no instrument failure; 2 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

qiaoruiyt/gsr officialmentioned in paperpytorchMITSyntology: 14 samples, 4 ran (2 instrument-failed) · 10 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

14 samples harvested: 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
2ran
10unverified

Licence: 0 of the 14 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 qiaoruiyt/gsr. “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.

qiaoruiyt/gsr official repository 14 samples, 4 ran (2 instrument-failed) · 10 unverified
StepLR gsr.py ran MIT (permissive) · 08917fa5845d4743 · report fixture: returned StepLR · level recorded 2026-09-22
WeightedObjective gsr.py ran MIT (permissive) · 6f1d4d10d1e5c202 · report fixture: returned WeightedObjective · level recorded 2026-09-22
evaluate_group_metrics gsr.py ran · our draft was wrong MIT (permissive) · e169611ba2ac5ecc · report fixture: signature model:callable/0/?, loader:SimpleLoader/0/?, device:str/0/str · returned tuple · level recorded 2026-09-22
get_scheduler in 122 papers gsr.py ran · our draft was wrong MIT (permissive) · 2864831366686f37 · report fixture: signature lr_scheduler_name:str/0/str, args:NoneType/0/? · returned StepLR · level recorded 2026-09-22
BaseInfluenceModule gsr.py unverified MIT (permissive) · 3fd80b99367c12ea · report
BaseObjective gsr.py unverified MIT (permissive) · 2c20ae130b043d1b · report
CGInfluenceModule gsr.py unverified MIT (permissive) · f479c3ef9035af3a · report
FastExactInfluenceModule gsr.py unverified MIT (permissive) · fc12323333290500 · report
FastHFInfluenceModule gsr.py unverified MIT (permissive) · 9b4e102e69368b30 · report
GSRTrainer gsr.py unverified MIT (permissive) · 63ab38b374ee2fc8 · report
LiSSAInfluenceModule gsr.py unverified MIT (permissive) · 8d4b41e721b86e4c · report
NoninvInfluenceModule gsr.py unverified MIT (permissive) · b1bcc58431353e09 · report
_del_attr gsr.py unverified MIT (permissive) · fe7f4afa378d85ca · report
_set_attr gsr.py unverified MIT (permissive) · 60d1488f20a46cd1 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for Group-robust Sample Reweighting (GSR) (graph method: Group-robust Sample Reweighting (GSR)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. update_aggregation_weights entry · level 2 · ran · 9f455aeaa9554f1e5ca8dd804760381eec61111a58b4066d27afaff518d86980

harvested Assembly for Group-robust Sample Reweighting (GSR) (graph method: Group-robust Sample Reweighting (GSR)). 15 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

  1. GSRTrainer entry · level 0 · unverified · 63ab38b374ee2fc8
  2. AverageMeter helper · level 1 · ran · 9355efdc819d943e
  3. CGInfluenceModule helper · level 0 · unverified · f479c3ef9035af3a
  4. FastExactInfluenceModule helper · level 0 · unverified · fc12323333290500
  5. FastHFInfluenceModule helper · level 0 · unverified · 9b4e102e69368b30
  6. LiSSAInfluenceModule helper · level 0 · unverified · 8d4b41e721b86e4c
  7. NoninvInfluenceModule helper · level 0 · unverified · b1bcc58431353e09
  8. WeightedObjective loss · level 1 · ran · 6f1d4d10d1e5c202
  9. evaluate_group_metrics helper · level 1 · ran · our draft was wrong · e169611ba2ac5ecc
  10. get_scheduler helper · level 1 · ran · our draft was wrong · 2864831366686f37
  11. BaseInfluenceModule helper · level 0 · unverified · 3fd80b99367c12ea
  12. BaseObjective helper · level 0 · unverified · 2c20ae130b043d1b
  13. StepLR helper · level 1 · ran · 08917fa5845d4743
  14. _del_attr helper · level 0 · unverified · fe7f4afa378d85ca
  15. _set_attr helper · level 0 · unverified · 60d1488f20a46cd1

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2503.07315") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ADOPTSET

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