{"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/tabmda-tabular-manifold-data-augmentation-for","title":"TabMDA: Tabular Manifold Data Augmentation for Any Classifier using Transformers with In-context Subsetting","arxiv_id":"2406.01805","date":"2024-06-03","proceeding":null,"authors":["Andrei Margeloiu","Adrián Bazaga","Nikola Simidjievski","Pietro Liò","Mateja Jamnik"],"abstract":"Tabular data is prevalent in many critical domains, yet it is often challenging to acquire in large quantities. This scarcity usually results in poor performance of machine learning models on such data. Data augmentation, a common strategy for performance improvement in vision and language tasks, typically underperforms for tabular data due to the lack of explicit symmetries in the input space. To overcome this challenge, we introduce TabMDA, a novel method for manifold data augmentation on tabular data. This method utilises a pre-trained in-context model, such as TabPFN, to map the data into an embedding space. TabMDA performs label-invariant transformations by encoding the data multiple times with varied contexts. This process explores the learned embedding space of the underlying in-context models, thereby enlarging the training dataset. TabMDA is a training-free method, making it applicable to any classifier. We evaluate TabMDA on five standard classifiers and observe significant performance improvements across various tabular datasets. Our results demonstrate that TabMDA provides an effective way to leverage information from pre-trained in-context models to enhance the performance of downstream classifiers. Code is available at https://github.com/AdrianBZG/TabMDA.","url_abs":"https://arxiv.org/abs/2406.01805v2","url_pdf":"https://arxiv.org/pdf/2406.01805v2.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":"tabmda-tabular-manifold-data-augmentation-for","repo_url":"https://github.com/adrianbzg/tabmda","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.01805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01805"}},"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/adrianbzg/tabmda","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":5},"by_repo_kind":{"official":{"samples":12,"ran":7,"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":"890fb6ef88c9dbef","entry":"JointBCELossWithLogits","repo":"adrianbzg/tabmda","repo_kind":"official","path":"TabPFN/tabpfn/losses.py","file_url":"https://github.com/adrianbzg/tabmda/blob/HEAD/TabPFN/tabpfn/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"890fb6ef88c9dbef"}},{"code_sha256_prefix":"16be270f8382bcf7","entry":"aggregate_metrics_across_batches","repo":"adrianbzg/tabmda","repo_kind":"official","path":"TabMDA/trainer.py","file_url":"https://github.com/adrianbzg/tabmda/blob/HEAD/TabMDA/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"16be270f8382bcf7"}},{"code_sha256_prefix":"174da700184e4073","entry":"calculate_similarities","repo":"adrianbzg/tabmda","repo_kind":"official","path":"utils.py","file_url":"https://github.com/adrianbzg/tabmda/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"174da700184e4073"}},{"code_sha256_prefix":"939b599ed6041748","entry":"get_append_embedding_encoder","repo":"adrianbzg/tabmda","repo_kind":"official","path":"TabPFN/tabpfn/encoders.py","file_url":"https://github.com/adrianbzg/tabmda/blob/HEAD/TabPFN/tabpfn/encoders.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"939b599ed6041748"}},{"code_sha256_prefix":"b7def069f21916ca","entry":"get_model_size","repo":"adrianbzg/tabmda","repo_kind":"official","path":"utils.py","file_url":"https://github.com/adrianbzg/tabmda/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b7def069f21916ca"}},{"code_sha256_prefix":"39f5dc76953cf6db","entry":"get_normalized_encoder","repo":"adrianbzg/tabmda","repo_kind":"official","path":"TabPFN/tabpfn/encoders.py","file_url":"https://github.com/adrianbzg/tabmda/blob/HEAD/TabPFN/tabpfn/encoders.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39f5dc76953cf6db"}},{"code_sha256_prefix":"79962b2f6a7e9c6c","entry":"to_numpy","repo":"adrianbzg/tabmda","repo_kind":"official","path":"utils.py","file_url":"https://github.com/adrianbzg/tabmda/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"79962b2f6a7e9c6c"}},{"code_sha256_prefix":"16eab2bd7416886c","entry":"get_normalized_uniform_encoder","repo":"adrianbzg/tabmda","repo_kind":"official","path":"TabPFN/tabpfn/encoders.py","file_url":"https://github.com/adrianbzg/tabmda/blob/HEAD/TabPFN/tabpfn/encoders.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"16eab2bd7416886c"}},{"code_sha256_prefix":"f1a940b32117c3d6","entry":"get_tabular_dataset","repo":"adrianbzg/tabmda","repo_kind":"official","path":"dataset/datasets.py","file_url":"https://github.com/adrianbzg/tabmda/blob/HEAD/dataset/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1a940b32117c3d6"}},{"code_sha256_prefix":"5e570d7cf36f11b5","entry":"get_torch_items","repo":"adrianbzg/tabmda","repo_kind":"official","path":"TabMDA/trainer.py","file_url":"https://github.com/adrianbzg/tabmda/blob/HEAD/TabMDA/trainer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5e570d7cf36f11b5"}},{"code_sha256_prefix":"ead008bd288520ca","entry":"load_oracle_test_indices","repo":"adrianbzg/tabmda","repo_kind":"official","path":"dataset/datasets.py","file_url":"https://github.com/adrianbzg/tabmda/blob/HEAD/dataset/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ead008bd288520ca"}},{"code_sha256_prefix":"c1354945204c381f","entry":"load_tabular_dataset","repo":"adrianbzg/tabmda","repo_kind":"official","path":"dataset/datasets.py","file_url":"https://github.com/adrianbzg/tabmda/blob/HEAD/dataset/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1354945204c381f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}