pith. sign in

Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 2

citation-polarity summary

fields

cs.CL 1 cs.LG 1

years

2026 2

roles

background 2

polarities

background 2

representative citing papers

Active Tabular Augmentation via Policy-Guided Diffusion Inpainting

cs.LG · 2026-05-11 · unverdicted · novelty 6.0

TAP couples a learner-conditioned policy with diffusion inpainting to generate and selectively inject high-utility tabular augmentations, yielding up to 15.6 pp accuracy gains and 32% RMSE reduction on seven datasets under severe scarcity.

citing papers explorer

Showing 2 of 2 citing papers.

  • Active Tabular Augmentation via Policy-Guided Diffusion Inpainting cs.LG · 2026-05-11 · unverdicted · none · ref 33

    TAP couples a learner-conditioned policy with diffusion inpainting to generate and selectively inject high-utility tabular augmentations, yielding up to 15.6 pp accuracy gains and 32% RMSE reduction on seven datasets under severe scarcity.

  • Model-Agnostic Meta Learning for Class Imbalance Adaptation cs.CL · 2026-04-20 · conditional · none · ref 3

    HAMR combines meta-learning with hardness-aware weighting and neighborhood resampling to improve minority-class performance on imbalanced NLP datasets.