{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/tabtransformer-tabular-data-modeling-using","title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","arxiv_id":"2012.06678","date":"2020-12-11","proceeding":null,"authors":["Xin Huang","Ashish Khetan","Milan Cvitkovic","Zohar Karnin"],"abstract":"We propose TabTransformer, a novel deep tabular data modeling architecture for supervised and semi-supervised learning. The TabTransformer is built upon self-attention based Transformers. The Transformer layers transform the embeddings of categorical features into robust contextual embeddings to achieve higher prediction accuracy. Through extensive experiments on fifteen publicly available datasets, we show that the TabTransformer outperforms the state-of-the-art deep learning methods for tabular data by at least 1.0% on mean AUC, and matches the performance of tree-based ensemble models. Furthermore, we demonstrate that the contextual embeddings learned from TabTransformer are highly robust against both missing and noisy data features, and provide better interpretability. Lastly, for the semi-supervised setting we develop an unsupervised pre-training procedure to learn data-driven contextual embeddings, resulting in an average 2.1% AUC lift over the state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2012.06678v1","url_pdf":"https://arxiv.org/pdf/2012.06678v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tabtransformer-tabular-data-modeling-using","repo_url":"https://github.com/lucidrains/tab-transformer-pytorch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tabtransformer-tabular-data-modeling-using","repo_url":"https://github.com/CyrilZhao-sudo/tab-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"tabtransformer-tabular-data-modeling-using","repo_url":"https://github.com/XavierSpycy/tabtransformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tabtransformer-tabular-data-modeling-using","repo_url":"https://github.com/anfreth/nampy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"tabtransformer-tabular-data-modeling-using","repo_url":"https://github.com/aruberts/TabTransformerTF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"tabtransformer-tabular-data-modeling-using","repo_url":"https://github.com/jpedrojpedro/transformers-tabular-data","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tabtransformer-tabular-data-modeling-using","repo_url":"https://github.com/jrzaurin/pytorch-widedeep","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"tabtransformer-tabular-data-modeling-using","repo_url":"https://github.com/manujosephv/pytorch_tabular","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tabtransformer-tabular-data-modeling-using","repo_url":"https://github.com/radi-cho/gatedtabtransformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tabtransformer-tabular-data-modeling-using","repo_url":"https://github.com/tylerjthomas9/TabularNetworks.jl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"tabtransformer-tabular-data-modeling-using","repo_url":"https://github.com/harshraj22/DeepLearning/tree/main/implementations/TabTransformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"tabtransformer-tabular-data-modeling-using","repo_url":"https://github.com/timeseriesAI/tsai/blob/main/tsai/models/TabTransformer.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"unsupervised-pre-training","task_name":"Unsupervised Pre-training"},{"task_slug":"tabular-classification","task_name":"tabular-classification"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tabtransformer","method_name":"TabTransformer"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[{"slug":"tabtransformer","name":"TabTransformer","full_name":"TabTransformer"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.06678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.06678"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/timeseriesAI/tsai/blob/main/tsai/models/TabTransformer.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/anfreth/nampy","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/harshraj22/DeepLearning/tree/main/implementations/TabTransformer","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aruberts/TabTransformerTF","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/XavierSpycy/tabtransformers","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/radi-cho/gatedtabtransformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jrzaurin/pytorch-widedeep","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CyrilZhao-sudo/tab-transformer","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/tab-transformer-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jpedrojpedro/transformers-tabular-data","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/manujosephv/pytorch_tabular","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tylerjthomas9/TabularNetworks.jl","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"5bbdefbbff4e08d8","entry":"FeedForward","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"5bbdefbbff4e08d8"}},{"code_sha256_prefix":"3f624c318bddcd17","entry":"load_bert","repo":"jpedrojpedro/transformers-tabular-data","repo_kind":"listed","path":"src/models.py","file_url":"https://github.com/jpedrojpedro/transformers-tabular-data/blob/HEAD/src/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3f624c318bddcd17"}},{"code_sha256_prefix":"01f60b1cabafb395","entry":"load_roberta","repo":"jpedrojpedro/transformers-tabular-data","repo_kind":"listed","path":"src/models.py","file_url":"https://github.com/jpedrojpedro/transformers-tabular-data/blob/HEAD/src/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"01f60b1cabafb395"}},{"code_sha256_prefix":"3d9cb9a2362dbcfe","entry":"load_t5","repo":"jpedrojpedro/transformers-tabular-data","repo_kind":"listed","path":"src/models.py","file_url":"https://github.com/jpedrojpedro/transformers-tabular-data/blob/HEAD/src/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3d9cb9a2362dbcfe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}