AI Paper Atlas

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

Segment-driven Structural Induction and Semantic Alignment for Heterogeneous Tabular Representation

Woojun Jung, Susik Yoon

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 0 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
add context-free attribute embedding (CAE) (ablation)NAVI · Product header predictionaccuracy: 0.5996 -> 0.9995Improved
add context-free attribute embedding (CAE) (ablation)NAVI · Movie value imputationaccuracy: 0.4799 -> 0.7077Improved
add context-free attribute embedding (CAE) (ablation)NAVI · Movie row classification (XGBoost)macro-F1: 0.265 -> 0.615Improved
add masked segment modeling instead of vanilla MLM (ablation)NAVI · Product value imputationaccuracy: 0.7769 -> 0.7933Improved
add masked segment modeling instead of vanilla MLM (ablation)NAVI · Movie row classification (XGBoost)macro-F1: 0.467 -> 0.615Improved
add entropy-driven segment alignment (ESA) (ablation)NAVI · Product value imputationaccuracy: 0.7977 -> 0.7933Hurt
add entropy-driven segment alignment (ESA) (ablation)NAVI · Product row classification (XGBoost)macro-F1: 0.909 -> 0.928Improved
add entropy-driven segment alignment (ESA) (ablation)NAVI · Movie row classification (XGBoost)macro-F1: 0.623 -> 0.615Hurt
use entropy-based routing instead of random routing in ESA (ablation)NAVI · Product row classification (XGBoost)macro-F1: 0.902 -> 0.928Improved
use entropy-based routing instead of random routing in ESA (ablation)NAVI · Movie row classification (XGBoost)macro-F1: 0.592 -> 0.615Improved
remove numerical columns (text-only) (ablation)NAVI · Product row classification (XGBoost)macro-F1: 0.928 -> 0.902Hurt
reduce textual coverage (partial-text) (ablation)NAVI · Product row classification (XGBoost)macro-F1: 0.928 -> 0.888Hurt

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