{"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/t2g-former-organizing-tabular-features-into","title":"T2G-Former: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction","arxiv_id":"2211.16887","date":"2022-11-30","proceeding":null,"authors":["Jiahuan Yan","Jintai Chen","Yixuan Wu","Danny Z. Chen","Jian Wu"],"abstract":"Recent development of deep neural networks (DNNs) for tabular learning has largely benefited from the capability of DNNs for automatic feature interaction. However, the heterogeneity nature of tabular features makes such features relatively independent, and developing effective methods to promote tabular feature interaction still remains an open problem. In this paper, we propose a novel Graph Estimator, which automatically estimates the relations among tabular features and builds graphs by assigning edges between related features. Such relation graphs organize independent tabular features into a kind of graph data such that interaction of nodes (tabular features) can be conducted in an orderly fashion. Based on our proposed Graph Estimator, we present a bespoke Transformer network tailored for tabular learning, called T2G-Former, which processes tabular data by performing tabular feature interaction guided by the relation graphs. A specific Cross-level Readout collects salient features predicted by the layers in T2G-Former across different levels, and attains global semantics for final prediction. Comprehensive experiments show that our T2G-Former achieves superior performance among DNNs and is competitive with non-deep Gradient Boosted Decision Tree models.","url_abs":"https://arxiv.org/abs/2211.16887v2","url_pdf":"https://arxiv.org/pdf/2211.16887v2.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":"t2g-former-organizing-tabular-features-into","repo_url":"https://github.com/jyansir/t2g-former","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"Relation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.16887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.16887"}},"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/jyansir/t2g-former","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran_violates":1,"unverified":9},"by_repo_kind":{"official":{"samples":13,"ran":4,"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":"d7bace13fb369137","entry":"geglu","repo":"jyansir/t2g-former","repo_kind":"official","path":"lib/deep.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/lib/deep.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7bace13fb369137"}},{"code_sha256_prefix":"9e66eafce9e7d0c5","entry":"needs_wd","repo":"jyansir/t2g-former","repo_kind":"official","path":"run_t2g.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/run_t2g.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e66eafce9e7d0c5"}},{"code_sha256_prefix":"2fb665ac3ecd7c20","entry":"reglu","repo":"jyansir/t2g-former","repo_kind":"official","path":"lib/deep.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/lib/deep.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2fb665ac3ecd7c20"}},{"code_sha256_prefix":"dc107686161af683","entry":"tanglu","repo":"jyansir/t2g-former","repo_kind":"official","path":"lib/deep.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/lib/deep.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc107686161af683"}},{"code_sha256_prefix":"556fd303cef00ac0","entry":"get_category_sizes","repo":"jyansir/t2g-former","repo_kind":"official","path":"lib/data.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/lib/data.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":"556fd303cef00ac0"}},{"code_sha256_prefix":"5363466fec65750c","entry":"get_path","repo":"jyansir/t2g-former","repo_kind":"official","path":"lib/env.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/lib/env.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":"5363466fec65750c"}},{"code_sha256_prefix":"a87e397491124834","entry":"get_relative_path","repo":"jyansir/t2g-former","repo_kind":"official","path":"lib/env.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/lib/env.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":"a87e397491124834"}},{"code_sha256_prefix":"e7ecc99fa574de72","entry":"glu","repo":"jyansir/t2g-former","repo_kind":"official","path":"bin/tabnet.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/bin/tabnet.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":"e7ecc99fa574de72"}},{"code_sha256_prefix":"b71e1c227eac8b6f","entry":"init_gbnn","repo":"jyansir/t2g-former","repo_kind":"official","path":"bin/grownet.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/bin/grownet.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":"b71e1c227eac8b6f"}},{"code_sha256_prefix":"bc1b01ffa8a77a76","entry":"needs_small_lr","repo":"jyansir/t2g-former","repo_kind":"official","path":"run_t2g.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/run_t2g.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":"bc1b01ffa8a77a76"}},{"code_sha256_prefix":"a6086df1a9be55e1","entry":"weighted_huber_loss","repo":"jyansir/t2g-former","repo_kind":"official","path":"lib/loss.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/lib/loss.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":"a6086df1a9be55e1"}},{"code_sha256_prefix":"84dcd60d1525cfef","entry":"weighted_l1_loss","repo":"jyansir/t2g-former","repo_kind":"official","path":"lib/loss.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/lib/loss.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":"84dcd60d1525cfef"}},{"code_sha256_prefix":"c2715046735f422e","entry":"weighted_mse_loss","repo":"jyansir/t2g-former","repo_kind":"official","path":"lib/loss.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/lib/loss.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":"c2715046735f422e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}