Papers › SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training

SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training

2 Jun 2021arXiv:2106.01342archive 2025-07-28

Gowthami Somepalli, Micah Goldblum, Avi Schwarzschild, C. Bayan Bruss, Tom Goldstein

Tabular data underpins numerous high-impact applications of machine learning from fraud detection to genomics and healthcare. Classical approaches to solving tabular problems, such as gradient boosting and random forests, are widely used by practitioners. However, recent deep learning methods have achieved a degree of performance competitive with popular techniques. We devise a hybrid deep learning approach to solving tabular data problems. Our method, SAINT, performs attention over both rows and columns, and it includes an enhanced embedding method. We also study a new contrastive self-supervised pre-training method for use when labels are scarce. SAINT consistently improves performance over previous deep learning methods, and it even outperforms gradient boosting methods, including XGBoost, CatBoost, and LightGBM, on average over a variety of benchmark tasks.

PaperPDFConference PDFCodeCode 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 26 code samples harvested from 4 repositories linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 2 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 13 samples from 1 repository, 12 ran (12 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 13 samples from 3 repositories, 7 ran (7 with no instrument failure; 0 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 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 19 samples that ran have no recorded date.

somepago/saint officialmentioned on GitHubpytorchApache-2.0Syntology: 13 samples, 12 ran (0 instrument-failed) · 1 unverified report
Actis92/lit-saint mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
Actis92/saint-lightning mentioned on GitHubpytorchMITSyntology: not harvested report
johanattia/tensorflow-saint mentioned on GitHubtfMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jrzaurin/pytorch-widedeep mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Revisiting Deep Learning Models for Tabular Data (arXiv:2106.11959; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 1 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
ogunlao/saint mentioned on GitHubpytorchMITSyntology: 9 samples, 3 ran (0 instrument-failed) · 6 unverified report
lucidrains/tab-transformer-pytorch pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Revisiting Deep Learning Models for Tabular Data (arXiv:2106.11959; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 1 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. 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.

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

26 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 2 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 7 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.

1ran · honoured contract
2ran · violated contract
16ran
7unverified

Licence: 13 of the 26 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 4 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. 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.

somepago/saint official repository 13 samples, 12 ran (0 instrument-failed) · 1 unverified
add_noise in 46 papers
census: 9 implementations from 9 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
augmentations.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · b042dc78ffec4ba8 · report fixture: signature x_categ:Tensor/2/int, x_cont:Tensor/2/float, noise_params:dict/0/? · returned tuple · level recorded 2026-09-25
concat_data data_openml.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 2d85447d6a2e686d · report fixture: signature X:dict/0/?, y:dict/0/? · returned DataFrame · level recorded 2026-09-25
count_parameters in 278 papers utils.py ran · honoured contract Apache-2.0 recorded; this copy not marked cleared · pointer only · f6b944f50d3f15ae · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
data_mask_split old_version/data.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 3c8af69a2bc14906 · report fixture: signature X:MockDataFrame/0/?, y:MockDataFrame/0/?, mask:MockDataFrame/0/?, y_mask:ndarray/1/float, indices:ndarray/1/int, mask_det:dict/0/?, stage:str/0/str · returned tuple · level recorded 2026-09-25
data_split in 17 papers data_openml.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · afcf8e4fc8cd0b4d · report fixture: signature X:DataFrame/0/?, y:ndarray/1/float, nan_mask:DataFrame/0/?, indices:ndarray/1/int · returned tuple · level recorded 2026-09-25
default in 430 papers models/model.py ran · violated contract fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 60fff7c3c400d7ff · report fixture: signature val:int/0/int, d:int/0/int · returned int · level recorded, date not recorded
embed_data_mask augmentations.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 4f7a0a76a82b38c7 · report fixture: signature x_categ:Tensor/2/int, x_cont:Tensor/2/float, cat_mask:Tensor/2/int, con_mask:Tensor/2/int, model:callable/0/?, vision_dset:bool/0/bool · returned tuple · level recorded 2026-09-25
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
models/model.py ran · violated contract Apache-2.0 recorded; this copy not marked cleared · pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
make_default_mask utils.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 6e97686ea3566edf · report fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-25
mixup_data in 51 papers augmentations.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 3f8482bac2c6b9db · report fixture: signature x1:Tensor/2/float, x2:Tensor/2/float, lam:float/0/float, y:Tensor/1/int, use_cuda:bool/0/bool · returned tuple · level recorded 2026-09-25
tag_gen utils.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 617821203b46f8a6 · report fixture: signature tag:str/0/str, y:dict/0/? · returned ndarray · level recorded 2026-09-25
task_dset_ids data_openml.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 04ca528d5c7c55fa · report fixture: signature task:str/0/str · returned list · level recorded 2026-09-26
ff_encodings models/model.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 8728271a97b8e7c5 · report
Actis92/lit-saint community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
cutmix in 11 papers src/lit_saint/augmentations.py ran MIT (permissive) · ea091d52c3e000f5 · report fixture: signature x:Tensor/2/float, random_index:Tensor/1/int, lam:float/0/float · returned Tensor · level recorded 2026-09-24
get_random_index src/lit_saint/augmentations.py ran fingerprinted MIT (permissive) · d07d3bae3af0c485 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
mixup in 28 papers src/lit_saint/augmentations.py ran MIT (permissive) · 1d107db8a201c1e5 · report fixture: signature x:Tensor/2/float, random_index:Tensor/1/int, lam:float/0/float · returned Tensor · level recorded 2026-09-24
johanattia/tensorflow-saint community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
feature_space_to_config src/rectransformer/feature.py ran MIT (permissive) · 6336169744f2eaf8 · report fixture: signature feature_space:MockFeatureSpace/0/? · returned NotImplementedType · level recorded 2026-09-24
ogunlao/saint community (archive-listed) 9 samples, 3 ran (0 instrument-failed) · 6 unverified
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
models/transformer.py ran MIT (permissive) · 525ff13ecf3ecd51 · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, dropout:callable/0/? · returned tuple · level recorded 2026-09-24
generate_dataset in 41 papers src/dataset.py ran MIT (permissive) · 7812364a72fefddf · report fixture: signature train_csv_path:str/0/str, val_csv_path:str/0/str, test_csv_path:str/0/str, train_y_csv_path:str/0/str, val_y_csv_path:str/0/str, test_y_csv_path:str/0/str · returned tuple · level recorded 2026-09-24
generate_splits src/dataset.py ran MIT (permissive) · 9785dbb6cb3ec3f0 · report fixture: signature dataset_size:int/0/int, num_supervised_train_data:int/0/int, validation_split:float/0/float, test_split:float/0/float, random_seed:int/0/int, shuffle_dataset:bool/0/bool · returned tuple · level recorded 2026-09-24
generate_dataloader src/dataloader.py unverified MIT (permissive) · e78cd941e1406260 · report
intersample models/saint_i.py unverified MIT (permissive) · 09d16d8b95917125 · report
make_saint models/saint.py unverified MIT (permissive) · 2f37195b67ea2d56 · report
make_saint_i models/saint_i.py unverified MIT (permissive) · 82133b453e0aa786 · report
make_saint_s models/saint_s.py unverified MIT (permissive) · aa5c35fec761ea99 · report

Tasks

Deep LearningFraud Detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: SAINT

CutMixDense ConnectionsFeedforward NetworkMixupSAINT

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