Research map / Image generation / GANs
GAIN: Missing Data Imputation using Generative Adversarial Nets
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the adversarial generator loss L_G (ablation) | GAIN · Breast | RMSE: .0701 ± .0021 -> .0546 ± .0006 | Helped |
| add the adversarial generator loss L_G (ablation) | GAIN · Spam | RMSE: .0676 ± .0029 -> .0513± .0016 | Helped |
| add the adversarial generator loss L_G (ablation) | GAIN · Letter | RMSE: .1344 ± .0012 -> .1198± .0005 | Helped |
| add the adversarial generator loss L_G (ablation) | GAIN · Credit | RMSE: .2436 ± .0012 -> .1858 ± .0010 | Helped |
| add the adversarial generator loss L_G (ablation) | GAIN · News | RMSE: .1612 ± .0024 -> .1441 ± .0007 | Helped |
| add the observed-value reconstruction loss L_M (ablation) | GAIN · Breast | RMSE: .0767 ± .0015 -> .0546 ± .0006 | Helped |
| add the observed-value reconstruction loss L_M (ablation) | GAIN · Spam | RMSE: .0672 ± .0036 -> .0513± .0016 | Helped |
| add the observed-value reconstruction loss L_M (ablation) | GAIN · Letter | RMSE: .1586 ± .0024 -> .1198± .0005 | Helped |
| add the observed-value reconstruction loss L_M (ablation) | GAIN · Credit | RMSE: .2533 ± .0048 -> .1858 ± .0010 | Helped |
| add the observed-value reconstruction loss L_M (ablation) | GAIN · News | RMSE: .2522 ± .0042 -> .1441 ± .0007 | Helped |
| add the hint mechanism (ablation) | GAIN · Breast | RMSE: .0639 ± .0018 -> .0546 ± .0006 | Helped |
| add the hint mechanism (ablation) | GAIN · Spam | RMSE: .0582 ± .0008 -> .0513± .0016 | Helped |
Closest papers by meaning
- Meta-GAIN for Missing Data Imputation (AAAI 2026 · similarity 0.93)
- GAMIN: Generative Adversarial Multiple Imputation Network for Highly Missing Data (CVPR 2020 · similarity 0.92)
- MisGAN: Learning from Incomplete Data with Generative Adversarial Networks (ICLR 2019 · similarity 0.92)
- Missing Data Imputation by Reducing Mutual Information with Rectified Flows (NeurIPS 2025 · similarity 0.87)
- DiffPuter: Empowering Diffusion Models for Missing Data Imputation (ICLR 2025 · similarity 0.85)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.84)
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.