Research map / Image generation / Fast diffusion sampling
RefiDiff: Progressive Refinement Diffusion for Efficient Missing Data Imputation
Md Atik Ahamed, Qiang Ye, Qiang Cheng
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add diffusion module on top of warm-up and polishing (ablation) | RefiDiff · Numerical, MAR, out-of-sample | RMSE x1e-2: 91.80 -> 73.82 | Improved |
| add diffusion module on top of warm-up and polishing (ablation) | RefiDiff · Numerical, MNAR, out-of-sample | RMSE x1e-2: 81.07 -> 70.12 | Improved |
| add diffusion module (ablation) | RefiDiff · Numerical, MCAR, in-sample | MAE: w/o Diff slightly lower in-sample MAE | Mixed |
| use CatBoost instead of XGBoost regressor (ablation) | RefiDiff · Numerical, all mechanisms | MAE/RMSE | No clear effect |
| use Mamba denoiser instead of TabDDPM-style DIFFPUTER denoiser (ablation) | imputation diffusion · California/Magic MNAR | runtime: about 4x faster | Improved |
| swap RefiDiff denoiser into DIFFPUTER | DIFFPUTER · Numerical imputation | MAE/RMSE | No clear effect |
| use RefiDiff instead of DIFFPUTER | imputation · Numerical, MNAR, in-sample | MAE x1e-2: 37.27 -> 34.49 | Improved |
| use RefiDiff instead of ReMasker | imputation · Categorical, MNAR, in-sample | accuracy (%): 63.01 -> 63.19 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DIFFPUTER — DiffPuter: Empowering Diffusion Models for Missing Data Imputation (ICLR 2025) · better on 8 of 9 shared results
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
- Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness (NeurIPS 2026 · similarity 0.91)
- Rethinking the Diffusion Models for Missing Data Imputation: A Gradient Flow Perspective (NeurIPS 2024 · similarity 0.88)
- DiffPuter: Empowering Diffusion Models for Missing Data Imputation (ICLR 2025 · similarity 0.88)
- Distribution Shift in Missing Data Imputation: A Risk-Based Perspective and Importance-Weighted Correction under MAR (NeurIPS 2026 · similarity 0.88)
- ProCTI: Prototype-Refined Global Conditioning for Diffusion-Based Time Series Imputation (NeurIPS 2026 · similarity 0.87)
- Missing Data Imputation by Reducing Mutual Information with Rectified Flows (NeurIPS 2025 · similarity 0.87)
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.
