AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Tabular Learnwares Can Be Repurposed for Seemingly Irrelevant New Tasks

Peng Tan, Feifan Yang, Zhi-Hao Tan, Zhi-Hua Zhou

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 1 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
guide feature mapping with a heuristically searched label mapping (cross-class performance matrix) (ablation)LwRepurpose · cross-task learnware reuse performancereuse accuracy distributionImproved
add system-recommended learnwares from other tasks via LwRepurposeuser self-trained model ensemble · TabZilla binary (limited labels)accuracy: 80.41 -> 81.12Improved
add system-recommended learnwares from other tasks via LwRepurposeuser LGBtuned ensemble · TabZilla binary (full labels)accuracy: 88.81 -> 89.17Improved
reuse learnwares from other tasks with previous distribution-matching adaptation (MMD, JOINT, GW, FA)model hub baselines · TabZilla binary (limited labels)accuracy gain after normalization: MMD -1.00, GW -0.35, JOINT -0.21, FA -0.03Hurt
use a shared backbone across diverse tasks (Xtab) instead of per-task modelsXtab · TabZilla binary (limited labels)accuracy: 52.30 vs 80.28 (TabPFNv2-basic)Hurt
optimize feature mapping on marginal distribution alone, then label mapping (no label guidance) (ablation)cross-task reuse · TabZilla binaryreuse accuracyHurt
recommend learnwares by estimated reuse performance (top-k)LwRepurpose · TabZilla binary learnware identificationaverage accuracy: 66.98% average -> close to oracle top-kImproved
ensemble a LightGBM learnware from an irrelevant task with a self-trained TabPFNlabel-scarce target tasks · TabZilla binary (limited labels)accuracy: gains up to 4.67 (Figure 4)Improved

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