Papers › Invariant Risk Minimization
Invariant Risk Minimization
Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, David Lopez-Paz
We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant correlations across multiple training distributions. To achieve this goal, IRM learns a data representation such that the optimal classifier, on top of that data representation, matches for all training distributions. Through theory and experiments, we show how the invariances learned by IRM relate to the causal structures governing the data and enable out-of-distribution generalization.
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):
get_harvested_code_for_paper(arxiv_id="1907.02893")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1907.02893", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1907.02893")
Code
No sample from the archive's official repository (facebookresearch/InvariantRiskMinimization) is linked to this paper; the 30 samples below come from 9 community repositories. Syntology harvested code from facebookresearch/InvariantRiskMinimization for another paper.
facebookresearch/InvariantRiskMinimization: Syntology's graph links these samples to Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization (arXiv:2311.11114; that paper's own run record: 28 ran (of which 5 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 6 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method.
Syntology 30 code samples harvested from 9 repositories linked to this paper: 18 ran (of which 6 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 2 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 30 samples from 9 repositories, 18 ran (12 with no instrument failure; 6 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.
No sample is linked to this paper from 5 of its repositories that Syntology harvested for other papers:
- facebookresearch/InvariantRiskMinimization, official repository: harvested for another paper, listed under the repository
- rwchakra/exmap, community (archive-listed): harvested for another paper, listed under the repository
- siddarth-c/FedGMA, community (archive-listed): harvested for another paper, listed under the repository
- thuml/Transfer-Learning-Library, community (archive-listed): harvested for 7 other papers, listed under the repository
- MindSpore-scientific-2/code-11, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 18 samples that ran have no recorded date.
18 repositories listed; official and paper-mentioned ones first.
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
30 samples harvested: 18 ran (of which 6 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 2 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 12 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.
Licence: 11 of the 30 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, 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 9 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.
2017c3948be2287e · report
fixture: returned InvariantRiskMinimization · level recorded 2026-09-22 7f8756cacd48bc13 · report
fixture: returned InvariantRiskMinimization · level recorded 2026-09-22 ccfb22f0237dbf06 · report
7901fe5f746966d4 · report
fixture: returned CGLBase · level recorded 2026-09-22 2f5e75c75135e52a · report
fixture: returned CGLearn · level recorded 2026-09-22 fac5364e2f53c6db · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded 28077f9c052f7aed · report
fixture: signature params:list/1/Tensor · returned tuple · level recorded, date not recorded cb517763d1083872 · report
fixture: signature losses:ndarray/1/float, preference:ndarray/1/float · returned float64 · level recorded, date not recorded 53fac8d8d949e72b · report
fixture: signature records:MockRecords/0/? · returned MockRecords · level recorded 2026-09-22 1fdaff04251a0d51 · report
fixture: signature dict_1:dict/0/?, dict_2:dict/0/? · returned Tensor · level recorded 2026-09-24 5f576ed342c48a0a · report
fixture: signature dataset:MinimalDataset/0/? · returned Tensor · level recorded 2026-09-24 32a5b544ec6bebb1 · report
fixture: signature losses:ndarray/2/float, val_accs:ndarray/1/float, test_accs:ndarray/1/float, anneal_iter:int/0/int, val_acc_bar:int/0/int, pood:NoneType/0/? · returned tuple · level recorded, date not recorded 196cab71d7129d62 · report
fixture: signature model:callable/0/? · returned MinimalResNet · level recorded 2026-09-24 6784a79e7943e224 · report
fixture: signature input_shape:tuple/1/int · returned MNIST_ResNet · level recorded 2026-09-24 9e81bbf308f5fd2b · report
4cc1b13edccacd97 · report
07696a6fad15378d · report
b0bc80b1655a6802 · report
d0ea85d74c20dea9 · report
73f32252eedba6a4 · report
af3c9a80c8fd1f7a · report
abbd8616af693ed0 · report
fixture: returned EarlyStopping · level recorded 2026-09-22 083ced6d4ac945b7 · report
fixture: signature vec:Tensor/2/float · returned Tensor · level recorded 2026-09-22 33b9f5baa6bc40fe · report
fixture: signature betas_e:list/1/Tensor, sigmas_e:list/1/Tensor · returned Tensor · level recorded 2026-09-22 db4d05619d1e83d4 · report
fixture: signature vector:Tensor/2/float · returned str · level recorded 2026-09-22 ac3dc229465a5881 · report
30536df61163084f · 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. 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
8 assemblies on this paper: 8 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
8 sibling assemblies for Invariant Risk Minimization (IRM) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Invariant Risk Minimization (IRM) (graph method: Invariant Risk Minimization (IRM)). 6 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- InvariantRiskMinimization entry · level 0 · unverified ·
30536df61163084f - BestParameters helper · level 0 · unverified ·
ac3dc229465a5881 - EarlyStopping helper · level 1 · ran ·
abbd8616af693ed0 - check_for_nans helper · level 1 · ran · violated contract ·
083ced6d4ac945b7 - popul_erm_solution helper · level 1 · ran · our draft was wrong ·
33b9f5baa6bc40fe - pretty helper · level 1 · ran · our draft was wrong ·
db4d05619d1e83d4
harvested Assembly for Invariant Risk Minimization (IRM) (graph method: Invariant Risk Minimization (IRM)). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- InvariantRiskMinimization entry · level 1 · ran ·
7f8756cacd48bc13 - pretty helper · level 1 · ran · our draft was wrong ·
db4d05619d1e83d4
harvested Assembly for Invariant Risk Minimization (IRM) (graph method: Invariant Risk Minimization (IRM)). 3 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 8 siblings
harvested Assembly for Invariant Risk Minimization (IRM) (graph method: Invariant Risk Minimization (IRM)). 13 bricks; individually on a fixture: 11 ran (of which 11 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 11 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 8 siblings
- IRM entry · level 1 · ran ·
d67283e16e562ca6 - Base helper · level 0 · unverified ·
18e936ebd670fd6a - FeatureCNN_seizure helper · level 1 · ran ·
b52a78200d301521 - FeatureCNN_sleep helper · level 1 · ran ·
3ac466a624f04b12 - GAMENet helper · level 1 · ran ·
ec6f05631fe21e1f - L_Concat helper · level 1 · ran ·
78feb2b545a636b1 - Retain helper · level 1 · ran ·
601c92322b549cff - Transformer helper · level 1 · ran ·
7bdbf9a1b404336b - ResBlock_seizure helper · level 1 · ran ·
9491922adfd487ae - ResBlock_sleep helper · level 1 · ran ·
beeb7b8e846ef784 - GCN helper · level 1 · ran ·
c7c1528707c4390d - get_last_visit helper · level 0 · unverified ·
dd2c5a50fe0a56af - GraphConvolution helper · level 1 · ran ·
d54315a68780fbba
harvested Assembly for Invariant Risk Minimization (IRM) (graph method: Invariant Risk Minimization (IRM)). 2 bricks; individually on a fixture: 2 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 8 siblings
- CGLearn entry · level 1 · ran ·
2f5e75c75135e52a - CGLBase model · level 1 · ran ·
7901fe5f746966d4
harvested Assembly for Invariant Risk Minimization (IRM) (graph method: Invariant Risk Minimization (IRM)). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- InvariantRiskMinimization entry · level 1 · ran ·
2017c3948be2287e - pretty helper · level 1 · ran · our draft was wrong ·
db4d05619d1e83d4
harvested Assembly for Invariant Risk Minimization (IRM) (graph method: Invariant Risk Minimization (IRM)). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- compute_penalty entry · level 0 · unverified ·
fe230835517bd55d
harvested Assembly for Invariant Risk Minimization (IRM) (graph method: Invariant Risk Minimization (IRM)). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- IRM entry · level 0 · unverified ·
ccfb22f0237dbf06
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="1907.02893") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Classification | Colored-MNIST(with spurious correlation) | MLP-IRM | Accuracy | 66.9 | #3 of 6 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
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