Official Implementations of "Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space""
Python · active 2023-10-11 → 2026-03-17 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 889 days from 2023-10-11 to 2026-03-17. Pushes: 7 total, peak 2 in a day. Pull requests: 18 total, peak 2 in a day. Issues: 34 total, peak 2 in a day. Comments: 73 total, peak 6 in a day. Stars: 159 total, peak 4 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| hengruizhang98 | 40 | 0 | 4 | 36 |
| jennyzhang0215 | 16 | 7 | 5 | 2 |
| jacobyokehongsi | 9 | 0 | 0 | 5 |
| QDKStorm | 7 | 0 | 1 | 3 |
| ZinebSN | 6 | 0 | 0 | 4 |
| JunHanStudy | 4 | 0 | 0 | 3 |
| YunjinPebblous | 4 | 0 | 0 | 3 |
| wxbs | 4 | 0 | 0 | 3 |
| kejinsen | 3 | 0 | 0 | 1 |
| jacobyhsi | 3 | 0 | 0 | 0 |
| juntongshi48 | 3 | 0 | 0 | 1 |
| ZhifengWu7 | 3 | 0 | 0 | 2 |
| Meeex2 | 3 | 0 | 1 | 0 |
| SeunghyunKim1995 | 2 | 0 | 0 | 1 |
| bruno686 | 2 | 0 | 0 | 1 |
| willyfh | 2 | 0 | 0 | 1 |
| zyf343865604 | 2 | 0 | 0 | 2 |
| AFEScalante | 2 | 0 | 2 | 0 |
| Yidadaa | 2 | 0 | 2 | 0 |
| uroskozole | 2 | 0 | 2 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#15dylanxp2025-10-08 15:00Hyperparameters for TabDDPM
- Pull request#41AFEScalante2025-08-14 16:39
- Pull request#41AFEScalante2025-08-05 18:55
- Issue comment#39rogerioagjr2025-07-17 20:20The command is missing for UDF conversion in README.md file.
- Issue#39Raju-Challagundla2025-05-16 06:21The command is missing for UDF conversion in README.md file.
- Pull request#38Meeex22025-05-13 07:38
- Issue#37Meeex22025-05-12 21:53ix ReduceLROnPlateau compatibility with newer PyTorch versions
- Pull request#36echosun19962025-04-29 04:55
- Issue#35KUKUDAS952025-03-28 02:15I have a question about learning.
- Issue comment#21QDKStorm2025-03-25 01:47Bug when Training Models
- Issue comment#21zyf3438656042025-03-24 06:40Bug when Training Models
- Issue comment#21zyf3438656042025-03-24 06:40Bug when Training Models
- Issue comment#27lakshaykakkar2025-02-12 16:56Details about the alpha precision evaluation
- Issue#34wxbs2025-01-15 16:38Generating the visualization of distributions of the DCR scores
- Issue comment#24reset05142025-01-09 08:26Problems with running VAE
- Issue#33jacobyhsi2025-01-08 00:42Training Convergence: AUC vs. Training Epoch
- Issue comment#17hengruizhang982024-12-27 13:05tabsyn works well in 50 dimensions but cannot be trained to work in 1000 dimensions.
- Issue comment#17wxbs2024-12-27 13:02tabsyn works well in 50 dimensions but cannot be trained to work in 1000 dimensions.
- Issue comment#17hengruizhang982024-12-27 12:42tabsyn works well in 50 dimensions but cannot be trained to work in 1000 dimensions.
- Issue comment#17wxbs2024-12-27 12:38tabsyn works well in 50 dimensions but cannot be trained to work in 1000 dimensions.
- Issue comment#17hengruizhang982024-12-27 12:31tabsyn works well in 50 dimensions but cannot be trained to work in 1000 dimensions.
- Issue comment#17wxbs2024-12-27 12:06tabsyn works well in 50 dimensions but cannot be trained to work in 1000 dimensions.
- Issue#31Ajoo2024-11-10 22:08VAE training using test loss to decay beta
- Issue#30LinoMMV2024-10-20 11:39Processing fails when dataset contains missing values.
- Issue comment#29hengruizhang982024-09-28 20:09Tabsyn Sampling Fails When Dataset Contains Only Categorical Features
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 159 stars here means stars gained during the window, not the repo's star count.