Papers › Revisiting Deep Learning Models for Tabular Data

Revisiting Deep Learning Models for Tabular Data

22 Jun 2021NeurIPS 2021 12arXiv:2106.11959archive 2025-07-28

Yury Gorishniy, Ivan Rubachev, Valentin Khrulkov, Artem Babenko

The existing literature on deep learning for tabular data proposes a wide range of novel architectures and reports competitive results on various datasets. However, the proposed models are usually not properly compared to each other and existing works often use different benchmarks and experiment protocols. As a result, it is unclear for both researchers and practitioners what models perform best. Additionally, the field still lacks effective baselines, that is, the easy-to-use models that provide competitive performance across different problems. In this work, we perform an overview of the main families of DL architectures for tabular data and raise the bar of baselines in tabular DL by identifying two simple and powerful deep architectures. The first one is a ResNet-like architecture which turns out to be a strong baseline that is often missing in prior works. The second model is our simple adaptation of the Transformer architecture for tabular data, which outperforms other solutions on most tasks. Both models are compared to many existing architectures on a diverse set of tasks under the same training and tuning protocols. We also compare the best DL models with Gradient Boosted Decision Trees and conclude that there is still no universally superior solution.

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 22 code samples harvested from 4 repositories linked to this paper: 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. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 10 ran (8 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 9 samples from 3 repositories, 8 ran (7 with no instrument failure; 1 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 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yandex-research/tabular-dl-revisiting-models officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: not harvested report
Yura52/tabular-dl-revisiting-models officialmentioned on GitHubpytorchApache-2.0Syntology: 13 samples, 10 ran (2 instrument-failed) · 3 unverified report
XavierSpycy/tabtransformers mentioned on GitHubpytorchMITSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
avinashbarnwal/Deep-Learning mentioned on GitHubpytorchSyntology: not harvested report
axrwl/fttransformer mentioned on GitHubjaxMITSyntology: not harvested report
jrzaurin/pytorch-widedeep mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lucidrains/tab-transformer-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
manujosephv/pytorch_tabular mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GANDALF: Gated Adaptive Network for Deep Automated Learning of Features (arXiv:2207.08548; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
yandex-research/rtdl-revisiting-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to OmniTabBench: Mapping the Empirical Frontiers of GBDTs, Neural Networks, and... (arXiv:2604.06814; that paper's own run record: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
aruberts/TabTransformerTF tfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to On Embeddings for Numerical Features in Tabular Deep Learning (arXiv:2203.05556; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
kalelpark/DeepLearning-for-Tabular-Data pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Revisiting Pretraining Objectives for Tabular Deep Learning (arXiv:2207.03208; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 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

22 samples harvested: 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. “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 · violated contract
3ran · our draft was wrong
14ran
4unverified

Licence: 1 of the 22 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 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.

Yura52/tabular-dl-revisiting-models official repository 13 samples, 10 ran (2 instrument-failed) · 3 unverified
geglu in 13 papers
census: 3 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
lib/deep.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · d7bace13fb369137 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
glu in 8 papers bin/tabnet.py ran Apache-2.0 (permissive) · e7ecc99fa574de72 · report fixture: signature act:EagerTensor/2/float, n_units:int/0/int · returned EagerTensor · level recorded 2026-09-26
init_gbnn bin/grownet.py ran fingerprinted Apache-2.0 (permissive) · b71e1c227eac8b6f · report fixture: signature y:ndarray/1/float · returned float · level recorded 2026-09-25
load_json in 344 papers lib/util.py ran Apache-2.0 (permissive) · 2f33af03ea909beb · report fixture: signature path:PosixPath/0/? · returned dict · level recorded 2026-09-25
load_pickle in 115 papers lib/util.py ran Apache-2.0 (permissive) · ba8f59b208956c3b · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-25
make_summary in 6 papers lib/metrics.py ran Apache-2.0 (permissive) · 9fb7a99bb9386bb6 · report fixture: signature metrics:dict/0/? · returned str · level recorded 2026-09-26
needs_wd bin/autoint.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · 9e66eafce9e7d0c5 · report fixture: signature name:str/0/str · returned bool · level recorded 2026-09-22
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
lib/data.py ran Apache-2.0 (permissive) · e9e943ad18a8b419 · report fixture: signature X:dict/0/?, normalization:str/0/str, seed:int/0/int, noise:float/0/float · returned dict · level recorded 2026-09-25
reglu in 12 papers
census: 3 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
lib/deep.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 2fb665ac3ecd7c20 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
to_tensors lib/data.py ran Apache-2.0 (permissive) · 33a6192b7abb8353 · report fixture: signature data:dict/0/? · returned dict · level recorded 2026-09-26
calculate_metrics in 61 papers lib/metrics.py unverified Apache-2.0 (permissive) · 12f448bfa8afc6b7 · report
load_dataset_info lib/data.py unverified Apache-2.0 (permissive) · 657558d2e8d19a32 · report
make_optimizer in 32 papers lib/deep.py unverified Apache-2.0 (permissive) · 27e9ee3019bc8ff0 · report
XavierSpycy/tabtransformers community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
f1_score_macro tabtransformers/metrics.py ran fingerprinted MIT (permissive) · 4d711eaf9f0bb383 · report fixture: signature y_true:ndarray/1/int, y_pred:ndarray/1/int · returned float · level recorded 2026-09-24
get_data in 223 papers tabtransformers/tools.py ran MIT (permissive) · f8e126db3b9cc8e1 · report fixture: signature data_path:str/0/str, split_val:bool/0/bool, data_files:dict/0/?, val_params:dict/0/?, index_col:NoneType/0/? · returned tuple · level recorded 2026-09-24
get_data_loader in 44 papers tabtransformers/tools.py ran MIT (permissive) · d29f63635e0b6468 · report fixture: signature train_dataset:TabularDataset/0/?, test_dataset:TabularDataset/0/?, val_dataset:TabularDataset/0/?, train_batch_size:int/0/int, inference_batch_size:int/0/int · returned tuple · level recorded 2026-09-24
get_loss_function in 11 papers tabtransformers/config.py ran MIT (permissive) · 516fa25431b82747 · report fixture: signature config:dict/0/? · returned MSELoss · level recorded 2026-09-24
load_config in 389 papers tabtransformers/config.py ran MIT (permissive) · d5ca06455ae6a9a5 · report fixture: signature config_path:str/0/str · returned dict · level recorded 2026-09-24
root_mean_squared_logarithmic_error tabtransformers/metrics.py ran fingerprinted MIT (permissive) · a18290fdacb1226e · report fixture: signature y_true:ndarray/1/float, y_pred:ndarray/1/float · returned float64 · level recorded 2026-09-24
get_model in 368 papers tabtransformers/config.py unverified MIT (permissive) · 6e2718cdfa77cc6a · report
jrzaurin/pytorch-widedeep community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_activation_fn in 67 papers pytorch_widedeep/models/_get_activation_fn.py ran Apache-2.0 (permissive) · 755bddefe05fb03e · report fixture: signature activation:str/0/str · returned ReLU · level recorded 2026-09-24
lucidrains/tab-transformer-pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
FeedForward in 198 papers tab_transformer_pytorch/ft_transformer.py ran · our draft was wrong MIT (permissive) · 5bbdefbbff4e08d8 · report fixture: signature dim:int/0/int, mult:int/0/int, dropout:float/0/float · returned Sequential · level recorded 2026-09-22

Tasks

Deep Learningtabular-classificationtabular-regression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutFT-TransformerLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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