AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Prior-free Tabular Test-time Adaptation

Rundong He, Jieming Shi

ICLR 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation

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
add class prior estimation (CPE) (ablation)PFT3A TabTransformer · Health Ins.accuracy: 58.29 -> 74.13Improved
add class prior estimation (CPE) (ablation)PFT3A TabTransformer · Hypertensionaccuracy: 59.45 -> 63.03Improved
add class prior estimation (CPE) (ablation)PFT3A TabTransformer · HELOCaccuracy: 60.46 -> 66.17Improved
add robust feature learning (RFL) (ablation)PFT3A TabTransformer · ANESaccuracy: 79.33 -> 80.33Improved
add robust feature learning (RFL) (ablation)PFT3A TabTransformer · ASSISTaccuracy: 58.39 -> 59.29Improved
add representative subspace exploration (RSE) (ablation)PFT3A TabTransformer · Health Ins.accuracy: 73.40 -> 74.13Improved
add representative subspace exploration (RSE) (ablation)PFT3A TabTransformer · Hypertensionaccuracy: 62.58 -> 63.03Improved
use PFT3A instead of FTATTabTransformer · TableShift (5 datasets avg)accuracy: 64.25 -> 68.59Improved
use PFT3A instead of Non-AdaptationTabTransformer · TableShift (5 datasets avg)F1: 59.92 -> 72.65Improved
apply generic TTA methods (TENT, EATA, CoTTA, ODS) instead of no adaptationTabTransformer · TableShift (5 datasets avg)accuracy: 60.77 -> 57.56Hurt
use dataset-specific hyperparameters instead of fixed ASSIST-tuned configurationPFT3A · Health Ins.accuracy: 74.13 -> 74.34No clear effect
use PFT3A with MLP backbone instead of FTATMLP · TableShift (5 datasets avg)accuracy: 64.51 -> 69.25Improved

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