{"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/carte-pretraining-and-transfer-for-tabular","title":"CARTE: Pretraining and Transfer for Tabular Learning","arxiv_id":"2402.16785","date":"2024-02-26","proceeding":null,"authors":["Myung Jun Kim","Léo Grinsztajn","Gaël Varoquaux"],"abstract":"Pretrained deep-learning models are the go-to solution for images or text. However, for tabular data the standard is still to train tree-based models. Indeed, transfer learning on tables hits the challenge of data integration: finding correspondences, correspondences in the entries (entity matching) where different words may denote the same entity, correspondences across columns (schema matching), which may come in different orders, names... We propose a neural architecture that does not need such correspondences. As a result, we can pretrain it on background data that has not been matched. The architecture -- CARTE for Context Aware Representation of Table Entries -- uses a graph representation of tabular (or relational) data to process tables with different columns, string embedding of entries and columns names to model an open vocabulary, and a graph-attentional network to contextualize entries with column names and neighboring entries. An extensive benchmark shows that CARTE facilitates learning, outperforming a solid set of baselines including the best tree-based models. CARTE also enables joint learning across tables with unmatched columns, enhancing a small table with bigger ones. CARTE opens the door to large pretrained models for tabular data.","url_abs":"https://arxiv.org/abs/2402.16785v2","url_pdf":"https://arxiv.org/pdf/2402.16785v2.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":"carte-pretraining-and-transfer-for-tabular","repo_url":"https://github.com/soda-inria/carte","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"data-integration","task_name":"Data Integration"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"aware","method_name":"AWARE"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.16785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16785"}},"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/soda-inria/carte","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":0,"samples":[{"code_sha256_prefix":"4b924c5969fa9958","entry":"carte_gridsearch","repo":"soda-inria/carte","repo_kind":"official","path":"carte_ai/src/carte_gridsearch.py","file_url":"https://github.com/soda-inria/carte/blob/HEAD/carte_ai/src/carte_gridsearch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4b924c5969fa9958"}},{"code_sha256_prefix":"d5b96afdb72d8b1e","entry":"generate_df_cdd","repo":"soda-inria/carte","repo_kind":"official","path":"carte_ai/src/visualization_utils.py","file_url":"https://github.com/soda-inria/carte/blob/HEAD/carte_ai/src/visualization_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d5b96afdb72d8b1e"}},{"code_sha256_prefix":"b3d047e62b963310","entry":"set_score_criterion","repo":"soda-inria/carte","repo_kind":"official","path":"carte_ai/src/evaluate_utils.py","file_url":"https://github.com/soda-inria/carte/blob/HEAD/carte_ai/src/evaluate_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b3d047e62b963310"}},{"code_sha256_prefix":"eaa00d5714148e18","entry":"set_split","repo":"soda-inria/carte","repo_kind":"official","path":"carte_ai/src/evaluate_utils.py","file_url":"https://github.com/soda-inria/carte/blob/HEAD/carte_ai/src/evaluate_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"eaa00d5714148e18"}},{"code_sha256_prefix":"3eb9de7b9abcc25a","entry":"sign_array","repo":"soda-inria/carte","repo_kind":"official","path":"carte_ai/src/visualization_utils.py","file_url":"https://github.com/soda-inria/carte/blob/HEAD/carte_ai/src/visualization_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3eb9de7b9abcc25a"}},{"code_sha256_prefix":"7e99a09bb11ae525","entry":"extract_llm_features","repo":"soda-inria/carte","repo_kind":"official","path":"carte_ai/src/preprocess_utils.py","file_url":"https://github.com/soda-inria/carte/blob/HEAD/carte_ai/src/preprocess_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7e99a09bb11ae525"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}