AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

TransTab: Learning Transferable Tabular Transformers Across Tables

Zifeng Wang, Jimeng Sun

NeurIPS 2022 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervision in supervised pipelines · 37 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use TransTab instead of the strongest baselineclinical-trial supervised learning · N00041119, N00174655, N00312208, N00079274, N00694382AUROC: 0.6397 -> 0.6408; 0.9310 -> 0.9428; 0.7586 -> 0.7770; 0.7178 -> 0.7281; 0.7458 -> 0.7648Improved
Use TransTab to learn from all three feature subsets instead of the strongest baselinefeature incremental learning · N00041119, N00174655, N00312208, N00079274, N00694382AUROC: 0.6371 -> 0.6797; 0.8485 -> 0.8545; 0.7031 -> 0.7617; 0.6535 -> 0.6857; 0.7236 -> 0.7795Improved
Pretrain across tables then finetune on the targetTransTab · clinical-trial mortality, across-table pretraining plus finetuningAUROC: 0.6313 -> 0.6405; 0.8348 -> 0.8583; 0.7444 -> 0.7517; 0.6885 -> 0.7063; 0.7293 -> 0.7392Improved
Use vanilla supervised transfer learning rather than no pretraining (ablation)TransTab · clinical-trial mortality, across-table pretraining plus finetuningAUROC: 0.6313 -> 0.6424; 0.8348 -> 0.8183; 0.7444 -> 0.7458; 0.6885 -> 0.6928; 0.7293 -> 0.7239Mixed
Use Self-VPCL rather than no pretraining (ablation)TransTab · public datasets, across-table pretraining plus finetuningAUROC: 0.763 -> 0.777; 0.858 -> 0.837; 0.630 -> 0.626; 0.907 -> 0.907; 0.841 -> 0.819; 0.844 -> 0.843; 0.821 -> 0.823; 0.919 ->Mixed
Use VPCL rather than no pretraining (ablation)TransTab · public datasets, across-table pretraining plus finetuningAUROC: 0.763 -> 0.776; 0.858 -> 0.858; 0.630 -> 0.637; 0.907 -> 0.907; 0.841 -> 0.862; 0.844 -> 0.844; 0.821 -> 0.819; 0.919 ->Mixed
Use zero-shot learning from set1+set2 instead of supervised learning on set3TransTab · clinical-trial mortality zero-shot learningAUROC: 0.5854 -> 0.5990; 0.6484 -> 0.6752; 0.7536 -> 0.7576; 0.7087 -> 0.7036; 0.6479 -> 0.6740Mixed
Use zero-shot learning from set1+set2 instead of supervised learning on set3TransTab · public datasets zero-shot learningAUROC: 0.581 -> 0.685; 0.635 -> 0.721; 0.571 -> 0.538; 0.898 -> 0.892; 0.733 -> 0.710; 0.822 -> 0.804; 0.702 -> 0.742; 0.875 ->Mixed
Pretrain on unrelated tables before finetuning (ablation)TransTab · public datasetsAUROC: 0.763 -> 0.776; 0.858 -> 0.858; 0.630 -> 0.637; 0.907 -> 0.907; 0.841 -> 0.862; 0.844 -> 0.844; 0.821 -> 0.819; 0.919 ->Mixed
Increase the number of vertical partitions (ablation)VPCL versus Self-VPCL · clinical-trial and public datasetsAUROCImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy