AI Paper Atlas

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

Table2Analysis: Modeling and Recommendation of Common Analysis Patterns for Multi-Dimensional Data

Mengyu Zhou, Wang Tao, Ji Pengxin, Han Shi, Zhang Dongmei

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 19 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 Search Sampling on top of pretrained model (ablation)Table2Analysis DQN · PivotTable test setR@1: 0.3108 -> 0.6518Improved
baseline scheduled sampling (DAD/MIXER-style) after pretrainingTable2Analysis DQN · PivotTable test setR@1: 0.3108 -> 0.0302Hurt
use large model instead of small (ablation)Table2Analysis DQN · DQN pretrain validationF1: 0.8415 -> 0.8939Improved
remove semantic embeddings (ablation)Table2Analysis DQN · DQN pretrain validationF1 (large): 0.8939 -> 0.8533Hurt
remove data statistic features (ablation)Table2Analysis DQN · DQN pretrain validationF1 (large): 0.8939 -> 0.8882Hurt
change loss class weight from (0.8,1) to (0.08,1) (ablation)Table2Analysis DQN · DQN pretrain validationF1 (large): 0.8939 -> 0.8086Hurt
OU-noise exploration instead of blind explore (ablation)Search Sampling · validation R@kR@kImproved
start Search Sampling from pretrained model instead of random init (ablation)Search Sampling · validation R@kR@k: 0.4823 vs 0.0121 at test R@5 (pretrain vs random)Improved
class weight 0.2 vs 0.8 during Search Sampling (ablation)Search Sampling · validation R@kR@kImproved

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