{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ACDW4TURABTZ2AZSG2RQMCRFZC","short_pith_number":"pith:ACDW4TUR","schema_version":"1.0","canonical_sha256":"00876e4e9100679d033236a3060a25c888c486483c38f823c3117d862b469dd7","source":{"kind":"arxiv","id":"2110.01889","version":3},"attestation_state":"computed","paper":{"title":"Deep Neural Networks and Tabular Data: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gjergji Kasneci, Johannes Haug, Kathrin Se{\\ss}ler, Martin Pawelczyk, Tobias Leemann, Vadim Borisov","submitted_at":"2021-10-05T09:22:39Z","abstract_excerpt":"Heterogeneous tabular data are the most commonly used form of data and are essential for numerous critical and computationally demanding applications. On homogeneous data sets, deep neural networks have repeatedly shown excellent performance and have therefore been widely adopted. However, their adaptation to tabular data for inference or data generation tasks remains challenging. To facilitate further progress in the field, this work provides an overview of state-of-the-art deep learning methods for tabular data. We categorize these methods into three groups: data transformations, specialized"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2110.01889","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-05T09:22:39Z","cross_cats_sorted":[],"title_canon_sha256":"6f2a89d627e0f9071d4f8c24769d65ee4d1fef1432889e17684c4e4c5f944950","abstract_canon_sha256":"6649ef7eb71117cc469ea75a5da981ec7ed794656fe75d90ef2e7467c8fb2afe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:42.261362Z","signature_b64":"peQkZtMq2d23PphRQOvK1id96Qg0lPPI3g5KjwCkbPtMQHfJKhbeOKCIYxgsqlzsfj7kpAwNMtCcaIGOlaVEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00876e4e9100679d033236a3060a25c888c486483c38f823c3117d862b469dd7","last_reissued_at":"2026-07-05T05:34:42.260849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:42.260849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Neural Networks and Tabular Data: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gjergji Kasneci, Johannes Haug, Kathrin Se{\\ss}ler, Martin Pawelczyk, Tobias Leemann, Vadim Borisov","submitted_at":"2021-10-05T09:22:39Z","abstract_excerpt":"Heterogeneous tabular data are the most commonly used form of data and are essential for numerous critical and computationally demanding applications. On homogeneous data sets, deep neural networks have repeatedly shown excellent performance and have therefore been widely adopted. However, their adaptation to tabular data for inference or data generation tasks remains challenging. To facilitate further progress in the field, this work provides an overview of state-of-the-art deep learning methods for tabular data. We categorize these methods into three groups: data transformations, specialized"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01889","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.01889/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.01889","created_at":"2026-07-05T05:34:42.260915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.01889v3","created_at":"2026-07-05T05:34:42.260915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01889","created_at":"2026-07-05T05:34:42.260915+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACDW4TURABTZ","created_at":"2026-07-05T05:34:42.260915+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACDW4TURABTZ2AZS","created_at":"2026-07-05T05:34:42.260915+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACDW4TUR","created_at":"2026-07-05T05:34:42.260915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24908","citing_title":"On the Impact of Class Imbalance on the Learning Dynamics of Deep Neural Networks:An Intuitive Insight","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2301.01864","citing_title":"AXIL: Exact Instance Attribution for Gradient Boosting","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2406.03506","citing_title":"Fuzzy Convolution Neural Networks for Tabular Data Classification","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2207.01848","citing_title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ACDW4TURABTZ2AZSG2RQMCRFZC","json":"https://pith.science/pith/ACDW4TURABTZ2AZSG2RQMCRFZC.json","graph_json":"https://pith.science/api/pith-number/ACDW4TURABTZ2AZSG2RQMCRFZC/graph.json","events_json":"https://pith.science/api/pith-number/ACDW4TURABTZ2AZSG2RQMCRFZC/events.json","paper":"https://pith.science/paper/ACDW4TUR"},"agent_actions":{"view_html":"https://pith.science/pith/ACDW4TURABTZ2AZSG2RQMCRFZC","download_json":"https://pith.science/pith/ACDW4TURABTZ2AZSG2RQMCRFZC.json","view_paper":"https://pith.science/paper/ACDW4TUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.01889&json=true","fetch_graph":"https://pith.science/api/pith-number/ACDW4TURABTZ2AZSG2RQMCRFZC/graph.json","fetch_events":"https://pith.science/api/pith-number/ACDW4TURABTZ2AZSG2RQMCRFZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACDW4TURABTZ2AZSG2RQMCRFZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACDW4TURABTZ2AZSG2RQMCRFZC/action/storage_attestation","attest_author":"https://pith.science/pith/ACDW4TURABTZ2AZSG2RQMCRFZC/action/author_attestation","sign_citation":"https://pith.science/pith/ACDW4TURABTZ2AZSG2RQMCRFZC/action/citation_signature","submit_replication":"https://pith.science/pith/ACDW4TURABTZ2AZSG2RQMCRFZC/action/replication_record"}},"created_at":"2026-07-05T05:34:42.260915+00:00","updated_at":"2026-07-05T05:34:42.260915+00:00"}