{"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/trompt-towards-a-better-deep-neural-network","title":"Trompt: Towards a Better Deep Neural Network for Tabular Data","arxiv_id":"2305.18446","date":"2023-05-29","proceeding":null,"authors":["Kuan-Yu Chen","Ping-Han Chiang","Hsin-Rung Chou","Ting-Wei Chen","Tien-Hao Chang"],"abstract":"Tabular data is arguably one of the most commonly used data structures in various practical domains, including finance, healthcare and e-commerce. The inherent heterogeneity allows tabular data to store rich information. However, based on a recently published tabular benchmark, we can see deep neural networks still fall behind tree-based models on tabular datasets. In this paper, we propose Trompt--which stands for Tabular Prompt--a novel architecture inspired by prompt learning of language models. The essence of prompt learning is to adjust a large pre-trained model through a set of prompts outside the model without directly modifying the model. Based on this idea, Trompt separates the learning strategy of tabular data into two parts. The first part, analogous to pre-trained models, focus on learning the intrinsic information of a table. The second part, analogous to prompts, focus on learning the variations among samples. Trompt is evaluated with the benchmark mentioned above. The experimental results demonstrate that Trompt outperforms state-of-the-art deep neural networks and is comparable to tree-based models.","url_abs":"https://arxiv.org/abs/2305.18446v2","url_pdf":"https://arxiv.org/pdf/2305.18446v2.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":[],"tasks":[{"task_slug":"prompt-learning","task_name":"Prompt Learning"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.18446","atlas_url":"https://app.syntology.ai/?focus=2305.18446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18446"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/LeoGrin/tabular-benchmark","reach":{"status":"ok"}}],"summary":{"ran":6},"by_repo_kind":{"found_in_text":{"samples":6,"ran":6,"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":6,"samples":[{"code_sha256_prefix":"40bd29725f53dbac","entry":"Attention","repo":"LeoGrin/tabular-benchmark","repo_kind":"found_in_text","path":"src/models/TabSurvey/models/tabtransformer.py","file_url":"https://github.com/LeoGrin/tabular-benchmark/blob/HEAD/src/models/TabSurvey/models/tabtransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"40bd29725f53dbac"}},{"code_sha256_prefix":"79f19d7a50807230","entry":"FeedForward","repo":"LeoGrin/tabular-benchmark","repo_kind":"found_in_text","path":"src/models/TabSurvey/models/tabtransformer.py","file_url":"https://github.com/LeoGrin/tabular-benchmark/blob/HEAD/src/models/TabSurvey/models/tabtransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"79f19d7a50807230"}},{"code_sha256_prefix":"8b3d1bc2a17e615c","entry":"GEGLU","repo":"LeoGrin/tabular-benchmark","repo_kind":"found_in_text","path":"src/models/TabSurvey/models/tabtransformer.py","file_url":"https://github.com/LeoGrin/tabular-benchmark/blob/HEAD/src/models/TabSurvey/models/tabtransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8b3d1bc2a17e615c"}},{"code_sha256_prefix":"637d14182deaf012","entry":"MLP","repo":"LeoGrin/tabular-benchmark","repo_kind":"found_in_text","path":"src/models/TabSurvey/models/tabtransformer.py","file_url":"https://github.com/LeoGrin/tabular-benchmark/blob/HEAD/src/models/TabSurvey/models/tabtransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"637d14182deaf012"}},{"code_sha256_prefix":"9fc4b5e8efb25766","entry":"TabTransformerModel","repo":"LeoGrin/tabular-benchmark","repo_kind":"found_in_text","path":"src/models/TabSurvey/models/tabtransformer.py","file_url":"https://github.com/LeoGrin/tabular-benchmark/blob/HEAD/src/models/TabSurvey/models/tabtransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fc4b5e8efb25766"}},{"code_sha256_prefix":"d9ee2b285d634e66","entry":"Transformer","repo":"LeoGrin/tabular-benchmark","repo_kind":"found_in_text","path":"src/models/TabSurvey/models/tabtransformer.py","file_url":"https://github.com/LeoGrin/tabular-benchmark/blob/HEAD/src/models/TabSurvey/models/tabtransformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d9ee2b285d634e66"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}