AI Paper Atlas

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

XTab: Cross-table Pretraining for Tabular Transformers

Bingzhao Zhu, Xingjian Shi, Nick Erickson, Mu Li, George Karypis, Mahsa Shoaran

ICML 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 6 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
Initialize FT-Transformer with cross-table pretrained weightsFT-Transformer on AMLB · AMLB downstream tasks, light finetuningwin rate: 71.0%Improved
Initialize FT-Transformer with cross-table pretrained weightsFT-Transformer on AMLB · AMLB downstream tasks, heavy finetuningwin rate: 56.1%Improved
Use reconstruction rather than contrastive or supervised pretraining (ablation)XTab with FT-Transformer · AMLB downstream tasks, light and heavy finetuningwin rate: 71.0%; 56.1%Improved
Use cross-table pretraining instead of random initializationFT-Transformer on AMLB 84 tasks · AMLB 84 tasks, default hyperparametersaverage rank: 10.19 ± 2.43 -> 9.21 ± 2.57Improved
Use cross-table pretraining instead of random initializationFT-Transformer on AMLB 84 tasks · AMLB 84 tasks, default hyperparametersaverage rank: 7.29 ± 2.20 -> 6.93 ± 2.09Improved
Use cross-table pretraining instead of random initializationFT-Transformer on AMLB 84 tasks · AMLB 84 tasks, default hyperparametersaverage rank: 4.94 ± 2.25 -> 4.39 ± 2.36Improved
Increase the number of cross-table pretraining tasks (ablation)XTab with FT-Transformer · AMLB downstream tasks, light finetuningwin rateImproved
Share all Transformer blocks rather than only the first block (ablation)XTab with FT-Transformer · AMLB downstream tasks, light finetuningwin rateImproved
Add the data-specific [CLS] token to the shared pretrained components (ablation)XTab with FT-Transformer · AMLB downstream tasks, light finetuningwin rateNo clear effect
Reduce downstream training data to 25%, 50%, or 75% (ablation)XTab with FT-Transformer · AMLB downstream taskswin rate over random initializationImproved
Reduce downstream training data (ablation)XTab with FT-Transformer · AMLB downstream tasksadvantage over baselineNo clear effect
Use 10 local FedAvg updates per aggregation rather than fewer local updates (ablation)XTab with FT-Transformer · AMLB downstream tasksdownstream performanceHurt

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