{"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/pytorch-frame-a-modular-framework-for-multi","title":"PyTorch Frame: A Modular Framework for Multi-Modal Tabular Learning","arxiv_id":"2404.00776","date":"2024-03-31","proceeding":null,"authors":["Weihua Hu","Yiwen Yuan","Zecheng Zhang","Akihiro Nitta","Kaidi Cao","Vid Kocijan","Jinu Sunil","Jure Leskovec","Matthias Fey"],"abstract":"We present PyTorch Frame, a PyTorch-based framework for deep learning over multi-modal tabular data. PyTorch Frame makes tabular deep learning easy by providing a PyTorch-based data structure to handle complex tabular data, introducing a model abstraction to enable modular implementation of tabular models, and allowing external foundation models to be incorporated to handle complex columns (e.g., LLMs for text columns). We demonstrate the usefulness of PyTorch Frame by implementing diverse tabular models in a modular way, successfully applying these models to complex multi-modal tabular data, and integrating our framework with PyTorch Geometric, a PyTorch library for Graph Neural Networks (GNNs), to perform end-to-end learning over relational databases.","url_abs":"https://arxiv.org/abs/2404.00776v2","url_pdf":"https://arxiv.org/pdf/2404.00776v2.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":"pytorch-frame-a-modular-framework-for-multi","repo_url":"https://github.com/pyg-team/pytorch-frame","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"toxic-comment-classification","task_name":"Toxic Comment Classification"}],"methods":[{"method_slug":null,"method_name":"Library"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/binary-classification-on-fake","task":"Binary Classification","dataset":"fake","model":"Trompt + OpenAI embedding","rank_in_archive_order":1,"of":8,"metrics":{"AUROC":"0.979"},"uses_additional_data":false},{"leaderboard":"/sota/binary-classification-on-fake","task":"Binary Classification","dataset":"fake","model":"LightGBM + OpenAI embedding","rank_in_archive_order":2,"of":8,"metrics":{"AUROC":"0.966"},"uses_additional_data":false},{"leaderboard":"/sota/binary-classification-on-fake","task":"Binary Classification","dataset":"fake","model":"FTTransformer + RoBERTa fintune","rank_in_archive_order":3,"of":8,"metrics":{"AUROC":"0.96"},"uses_additional_data":false},{"leaderboard":"/sota/binary-classification-on-fake","task":"Binary Classification","dataset":"fake","model":"LightGBM + RoBERTa embedding","rank_in_archive_order":4,"of":8,"metrics":{"AUROC":"0.954"},"uses_additional_data":false},{"leaderboard":"/sota/binary-classification-on-fake","task":"Binary Classification","dataset":"fake","model":"FTTransformer + RoBERTa embedding","rank_in_archive_order":5,"of":8,"metrics":{"AUROC":"0.936"},"uses_additional_data":false},{"leaderboard":"/sota/binary-classification-on-fake","task":"Binary Classification","dataset":"fake","model":"ResNet + RoBERTa embedding","rank_in_archive_order":6,"of":8,"metrics":{"AUROC":"0.934"},"uses_additional_data":false},{"leaderboard":"/sota/binary-classification-on-fake","task":"Binary Classification","dataset":"fake","model":"ResNet + OpenAI embedding","rank_in_archive_order":7,"of":8,"metrics":{"AUROC":"0.923"},"uses_additional_data":false},{"leaderboard":"/sota/binary-classification-on-fake","task":"Binary Classification","dataset":"fake","model":"FTTransformer + OpenAI embedding","rank_in_archive_order":8,"of":8,"metrics":{"AUROC":"0.911"},"uses_additional_data":false},{"leaderboard":"/sota/binary-classification-on-kickstarter","task":"Binary Classification","dataset":"kickstarter","model":"Trompt + OpenAI embedding","rank_in_archive_order":1,"of":4,"metrics":{"AUROC":"0.81"},"uses_additional_data":false},{"leaderboard":"/sota/binary-classification-on-kickstarter","task":"Binary Classification","dataset":"kickstarter","model":"ResNet + RoBERTa finetune","rank_in_archive_order":3,"of":4,"metrics":{"AUROC":"0.786"},"uses_additional_data":false},{"leaderboard":"/sota/binary-classification-on-kickstarter","task":"Binary Classification","dataset":"kickstarter","model":"LightGBM + RoBERTa embedding","rank_in_archive_order":4,"of":4,"metrics":{"AUROC":"0.767"},"uses_additional_data":false},{"leaderboard":"/sota/toxic-comment-classification-on-civil","task":"Toxic Comment Classification","dataset":"Civil Comments","model":"ResNet + RoBERTa finetune","rank_in_archive_order":15,"of":22,"metrics":{"AUROC":"0.97"},"uses_additional_data":false},{"leaderboard":"/sota/toxic-comment-classification-on-civil","task":"Toxic Comment Classification","dataset":"Civil Comments","model":"Trompt + OpenAI embedding","rank_in_archive_order":16,"of":22,"metrics":{"AUROC":"0.947"},"uses_additional_data":false},{"leaderboard":"/sota/toxic-comment-classification-on-civil","task":"Toxic Comment Classification","dataset":"Civil Comments","model":"ResNet + OpenAI embedding","rank_in_archive_order":17,"of":22,"metrics":{"AUROC":"0.945"},"uses_additional_data":false},{"leaderboard":"/sota/toxic-comment-classification-on-civil","task":"Toxic Comment Classification","dataset":"Civil Comments","model":"Trompt + RoBERTa embedding","rank_in_archive_order":18,"of":22,"metrics":{"AUROC":"0.885"},"uses_additional_data":false},{"leaderboard":"/sota/toxic-comment-classification-on-civil","task":"Toxic Comment Classification","dataset":"Civil Comments","model":"ResNet + RoBERTa embedding","rank_in_archive_order":19,"of":22,"metrics":{"AUROC":"0.882"},"uses_additional_data":false},{"leaderboard":"/sota/toxic-comment-classification-on-civil","task":"Toxic Comment Classification","dataset":"Civil Comments","model":"LightGBM + RoBERTa embedding","rank_in_archive_order":20,"of":22,"metrics":{"AUROC":"0.865"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.00776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00776"}},"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/pyg-team/pytorch-frame","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"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":0,"samples":[{"code_sha256_prefix":"565652dbf68ada7e","entry":"embeddings_with_backoff","repo":"pyg-team/pytorch-frame","repo_kind":"official","path":"benchmark/data_frame_text_benchmark.py","file_url":"https://github.com/pyg-team/pytorch-frame/blob/HEAD/benchmark/data_frame_text_benchmark.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":"565652dbf68ada7e"}},{"code_sha256_prefix":"fcebd39e1e7bde51","entry":"mean_pooling","repo":"pyg-team/pytorch-frame","repo_kind":"official","path":"benchmark/data_frame_text_benchmark.py","file_url":"https://github.com/pyg-team/pytorch-frame/blob/HEAD/benchmark/data_frame_text_benchmark.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fcebd39e1e7bde51"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}