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 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="2106.01342")

Code

Syntology Ran 3 of 26 code samples harvested from 4 repositories linked to this paper; 23 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · violated contract.

By repository: official repository: 13 samples from 1 repository, 3 ran; community (archive-listed): 13 samples from 3 repositories, 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.

somepago/saint officialmentioned on GitHubpytorchApache-2.0 report
Actis92/lit-saint mentioned on GitHubpytorchMIT report
Actis92/saint-lightning mentioned on GitHubpytorchMIT report
johanattia/tensorflow-saint mentioned on GitHubtfMIT report
jrzaurin/pytorch-widedeep mentioned on GitHubpytorchApache-2.0 report
ogunlao/saint mentioned on GitHubpytorchMIT 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

26 samples harvested; 3 ran; 1 honoured the contract we drafted; 23 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.

1ran · honoured contract
2ran · violated contract
23unverified

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; each sample names its own and says which. “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.

count_parameters somepago/saint/utils.py official repository ran · honoured contract Apache-2.0 recorded; this copy not marked cleared · pointer only · f6b944f50d3f15ae · report
default somepago/saint/models/model.py official repository ran · violated contract fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 60fff7c3c400d7ff · report
exists somepago/saint/models/model.py official repository ran · violated contract Apache-2.0 recorded; this copy not marked cleared · pointer only · aa5486a3650902d8 · report
add_noise somepago/saint/augmentations.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · b042dc78ffec4ba8 · report
concat_data somepago/saint/data_openml.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 2d85447d6a2e686d · report
data_mask_split somepago/saint/old_version/data.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 3c8af69a2bc14906 · report
data_split somepago/saint/data_openml.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · afcf8e4fc8cd0b4d · report
embed_data_mask somepago/saint/augmentations.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 4f7a0a76a82b38c7 · report
ff_encodings somepago/saint/models/model.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 8728271a97b8e7c5 · report
make_default_mask somepago/saint/utils.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 6e97686ea3566edf · report
mixup_data somepago/saint/augmentations.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 3f8482bac2c6b9db · report
tag_gen somepago/saint/utils.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 617821203b46f8a6 · report
task_dset_ids somepago/saint/data_openml.py official repository unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 04ca528d5c7c55fa · report
attention ogunlao/saint/models/transformer.py community (archive-listed) unverified MIT (permissive) · 525ff13ecf3ecd51 · report
cutmix Actis92/lit-saint/src/lit_saint/augmentations.py community (archive-listed) unverified MIT (permissive) · ea091d52c3e000f5 · report
feature_space_to_config johanattia/tensorflow-saint/src/rectransformer/feature.py community (archive-listed) unverified MIT (permissive) · 6336169744f2eaf8 · report
generate_dataloader ogunlao/saint/src/dataloader.py community (archive-listed) unverified MIT (permissive) · e78cd941e1406260 · report
generate_dataset ogunlao/saint/src/dataset.py community (archive-listed) unverified MIT (permissive) · 7812364a72fefddf · report
generate_splits ogunlao/saint/src/dataset.py community (archive-listed) unverified MIT (permissive) · 9785dbb6cb3ec3f0 · report
get_random_index Actis92/lit-saint/src/lit_saint/augmentations.py community (archive-listed) unverified MIT (permissive) · d07d3bae3af0c485 · report
intersample ogunlao/saint/models/saint_i.py community (archive-listed) unverified MIT (permissive) · 09d16d8b95917125 · report
make_saint ogunlao/saint/models/saint.py community (archive-listed) unverified MIT (permissive) · 2f37195b67ea2d56 · report
make_saint_i ogunlao/saint/models/saint_i.py community (archive-listed) unverified MIT (permissive) · 82133b453e0aa786 · report
make_saint_s ogunlao/saint/models/saint_s.py community (archive-listed) unverified MIT (permissive) · aa5c35fec761ea99 · report
mixup Actis92/lit-saint/src/lit_saint/augmentations.py community (archive-listed) unverified MIT (permissive) · 1d107db8a201c1e5 · report
preprocess ogunlao/saint/src/dataset.py community (archive-listed) unverified MIT (permissive) · 957d6b14b7e5575a · 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