AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

STaSy: Score-based Tabular data Synthesis

Jayoung Kim, Chaejeong Lee, Noseong Park

ICLR 2023 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion · 9 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
Use score-based tabular synthesis with self-paced learning and fine-tuningSTaSy · 15-dataset averagequality (F1 & R²): 0.717 -> 0.733Improved
Use score-based tabular synthesis with self-paced learning and fine-tuningSTaSy · 15-dataset averagediversity (coverage): 0.637 -> 0.658Improved
Add self-paced learning and fine-tuning to Naïve-STaSy (ablation)STaSy · 15-dataset TSTR averageF1: 0.777 -> 0.792Improved
Add self-paced learning and fine-tuning to Naïve-STaSy (ablation)STaSy · 15-dataset averageruntime (second): 8.855 -> 10.663Hurt
Add fine-tuning (ablation)STaSy · testing records, averaged over datasetsmedian log-probability: 129.293 -> 131.734Improved
Add self-paced learning (ablation)STaSy · sampling diversity across datasetscoverageImproved
Fine-tune with denoising score matching loss rather than Hutchinson estimation (ablation)STaSy · DefaultF1: 0.510 -> 0.523Improved
Fine-tune with denoising score matching loss rather than Hutchinson estimation (ablation)STaSy · ContraceptiveF1: 0.438 -> 0.451Improved
Use probability flow instead of predictor-corrector reverse-SDE solvers (ablation)Naïve-STaSy · MagicF1: AS: 0.752 -> 0.777; RD: 0.779 -> 0.775; EM: 0.779 -> 0.771Mixed
Add self-paced learning to STaSy oversampling (ablation)STaSy w/o fine-tuning · HTRU, Magic, and RobotWeighted-F1: 0.8767 -> 0.8803; 0.7807 -> 0.7960; 0.9031 -> 0.9270Improved

Later papers that compared with this method

3 later accepted papers report STaSy as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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