{"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/revisiting-pretraining-objectives-for-tabular","title":"Revisiting Pretraining Objectives for Tabular Deep Learning","arxiv_id":"2207.03208","date":"2022-07-07","proceeding":null,"authors":["Ivan Rubachev","Artem Alekberov","Yury Gorishniy","Artem Babenko"],"abstract":"Recent deep learning models for tabular data currently compete with the traditional ML models based on decision trees (GBDT). Unlike GBDT, deep models can additionally benefit from pretraining, which is a workhorse of DL for vision and NLP. For tabular problems, several pretraining methods were proposed, but it is not entirely clear if pretraining provides consistent noticeable improvements and what method should be used, since the methods are often not compared to each other or comparison is limited to the simplest MLP architectures. In this work, we aim to identify the best practices to pretrain tabular DL models that can be universally applied to different datasets and architectures. Among our findings, we show that using the object target labels during the pretraining stage is beneficial for the downstream performance and advocate several target-aware pretraining objectives. Overall, our experiments demonstrate that properly performed pretraining significantly increases the performance of tabular DL models, which often leads to their superiority over GBDTs.","url_abs":"https://arxiv.org/abs/2207.03208v2","url_pdf":"https://arxiv.org/pdf/2207.03208v2.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":"revisiting-pretraining-objectives-for-tabular","repo_url":"https://github.com/puhsu/tabular-dl-pretrain-objectives","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"revisiting-pretraining-objectives-for-tabular","repo_url":"https://github.com/kalelpark/DeepLearning-for-Tabular-Data","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.03208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.03208"}},"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/puhsu/tabular-dl-pretrain-objectives","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kalelpark/DeepLearning-for-Tabular-Data","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"unverified":10},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":11,"ran":2,"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":1,"samples":[{"code_sha256_prefix":"d7bace13fb369137","entry":"geglu","repo":"kalelpark/DeepLearning-for-Tabular-Data","repo_kind":"listed","path":"model/fttransformer.py","file_url":"https://github.com/kalelpark/DeepLearning-for-Tabular-Data/blob/HEAD/model/fttransformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d7bace13fb369137"}},{"code_sha256_prefix":"2fb665ac3ecd7c20","entry":"reglu","repo":"kalelpark/DeepLearning-for-Tabular-Data","repo_kind":"listed","path":"model/fttransformer.py","file_url":"https://github.com/kalelpark/DeepLearning-for-Tabular-Data/blob/HEAD/model/fttransformer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2fb665ac3ecd7c20"}},{"code_sha256_prefix":"267506bc9a077f62","entry":"geglu","repo":"kalelpark/DeepLearning-for-Tabular-Data","repo_kind":"listed","path":"model/common.py","file_url":"https://github.com/kalelpark/DeepLearning-for-Tabular-Data/blob/HEAD/model/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"267506bc9a077f62"}},{"code_sha256_prefix":"654f1fcd1eb02728","entry":"gen_masks","repo":"puhsu/tabular-dl-pretrain-objectives","repo_kind":"official","path":"bin/contrastive.py","file_url":"https://github.com/puhsu/tabular-dl-pretrain-objectives/blob/HEAD/bin/contrastive.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":"654f1fcd1eb02728"}},{"code_sha256_prefix":"3516d62bde618799","entry":"get_DataLoader","repo":"kalelpark/DeepLearning-for-Tabular-Data","repo_kind":"listed","path":"dataset.py","file_url":"https://github.com/kalelpark/DeepLearning-for-Tabular-Data/blob/HEAD/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3516d62bde618799"}},{"code_sha256_prefix":"755cfe893c1d9d02","entry":"get_accuracy_score","repo":"kalelpark/DeepLearning-for-Tabular-Data","repo_kind":"listed","path":"metrics.py","file_url":"https://github.com/kalelpark/DeepLearning-for-Tabular-Data/blob/HEAD/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"755cfe893c1d9d02"}},{"code_sha256_prefix":"95e5ab23ac9b1697","entry":"get_loss","repo":"kalelpark/DeepLearning-for-Tabular-Data","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/kalelpark/DeepLearning-for-Tabular-Data/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"95e5ab23ac9b1697"}},{"code_sha256_prefix":"38f46a7da72f1a57","entry":"get_optimizer","repo":"kalelpark/DeepLearning-for-Tabular-Data","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/kalelpark/DeepLearning-for-Tabular-Data/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"38f46a7da72f1a57"}},{"code_sha256_prefix":"8b0c1b12fef2c111","entry":"get_rmse_score","repo":"kalelpark/DeepLearning-for-Tabular-Data","repo_kind":"listed","path":"metrics.py","file_url":"https://github.com/kalelpark/DeepLearning-for-Tabular-Data/blob/HEAD/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8b0c1b12fef2c111"}},{"code_sha256_prefix":"003cd9aa1bf19f07","entry":"load_dataset","repo":"kalelpark/DeepLearning-for-Tabular-Data","repo_kind":"listed","path":"dataset.py","file_url":"https://github.com/kalelpark/DeepLearning-for-Tabular-Data/blob/HEAD/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"003cd9aa1bf19f07"}},{"code_sha256_prefix":"d13ea26797a378f5","entry":"load_model","repo":"kalelpark/DeepLearning-for-Tabular-Data","repo_kind":"listed","path":"model/common.py","file_url":"https://github.com/kalelpark/DeepLearning-for-Tabular-Data/blob/HEAD/model/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d13ea26797a378f5"}},{"code_sha256_prefix":"618ead3731b2c637","entry":"reglu","repo":"kalelpark/DeepLearning-for-Tabular-Data","repo_kind":"listed","path":"model/common.py","file_url":"https://github.com/kalelpark/DeepLearning-for-Tabular-Data/blob/HEAD/model/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"618ead3731b2c637"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}