{"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/interpretabnet-distilling-predictive-signals","title":"InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation","arxiv_id":"2406.00426","date":"2024-06-01","proceeding":null,"authors":["Jacob Si","Wendy Yusi Cheng","Michael Cooper","Rahul G. Krishnan"],"abstract":"Tabular data are omnipresent in various sectors of industries. Neural networks for tabular data such as TabNet have been proposed to make predictions while leveraging the attention mechanism for interpretability. However, the inferred attention masks are often dense, making it challenging to come up with rationales about the predictive signal. To remedy this, we propose InterpreTabNet, a variant of the TabNet model that models the attention mechanism as a latent variable sampled from a Gumbel-Softmax distribution. This enables us to regularize the model to learn distinct concepts in the attention masks via a KL Divergence regularizer. It prevents overlapping feature selection by promoting sparsity which maximizes the model's efficacy and improves interpretability to determine the important features when predicting the outcome. To assist in the interpretation of feature interdependencies from our model, we employ a large language model (GPT-4) and use prompt engineering to map from the learned feature mask onto natural language text describing the learned signal. Through comprehensive experiments on real-world datasets, we demonstrate that InterpreTabNet outperforms previous methods for interpreting tabular data while attaining competitive accuracy.","url_abs":"https://arxiv.org/abs/2406.00426v3","url_pdf":"https://arxiv.org/pdf/2406.00426v3.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":"interpretabnet-distilling-predictive-signals","repo_url":"https://github.com/jacobyhsi/InterpreTabNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feature-selection","method_name":"Feature Selection"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"tabnet","method_name":"TabNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.00426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00426"}},"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/jacobyhsi/InterpreTabNet","reach":null}],"summary":{"ran":10,"unverified":5},"by_repo_kind":{"official":{"samples":15,"ran":10,"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":"32d61856363edf25","entry":"EmbeddingGenerator","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"32d61856363edf25"}},{"code_sha256_prefix":"534e36abacbedbee","entry":"Entmax15","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"534e36abacbedbee"}},{"code_sha256_prefix":"8fc8e9f7a0141422","entry":"Entmax15Function","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"8fc8e9f7a0141422"}},{"code_sha256_prefix":"87a7c3a7f5cab073","entry":"FeatTransformer","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"87a7c3a7f5cab073"}},{"code_sha256_prefix":"7ad035217e9fa718","entry":"GBN","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"7ad035217e9fa718"}},{"code_sha256_prefix":"bda5ab5fc12e96df","entry":"GLU_Block","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"bda5ab5fc12e96df"}},{"code_sha256_prefix":"5861b1716a0a0046","entry":"GLU_Layer","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"5861b1716a0a0046"}},{"code_sha256_prefix":"9ad4e49330a00585","entry":"Sparsemax","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"9ad4e49330a00585"}},{"code_sha256_prefix":"fd64f23efb357294","entry":"SparsemaxFunction","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"fd64f23efb357294"}},{"code_sha256_prefix":"e2353d85a4193ce6","entry":"TabNetEncoder","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"e2353d85a4193ce6"}},{"code_sha256_prefix":"072b418dfe2df0ba","entry":"AttentiveTransformer","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"072b418dfe2df0ba"}},{"code_sha256_prefix":"ccadc817f4a9d1a2","entry":"TabNet","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"ccadc817f4a9d1a2"}},{"code_sha256_prefix":"440701a70b477120","entry":"TabNetNoEmbeddings","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"440701a70b477120"}},{"code_sha256_prefix":"7690965dab7e21e6","entry":"initialize_glu","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"7690965dab7e21e6"}},{"code_sha256_prefix":"ed1b885a712fb350","entry":"initialize_non_glu","repo":"jacobyhsi/InterpreTabNet","repo_kind":"official","path":"pytorch_tabnet/tab_network.py","file_url":"https://github.com/jacobyhsi/InterpreTabNet/blob/HEAD/pytorch_tabnet/tab_network.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":"ed1b885a712fb350"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}