Official implementation of the paper "FilterNet: Harnessing Frequency Filters for Time Series Forecasting"
active 2024-11-03 → 2026-03-11 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 494 days from 2024-11-03 to 2026-03-11. Pushes: 9 total, peak 6 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 8 total, peak 1 in a day. Comments: 6 total, peak 2 in a day. Stars: 107 total, peak 6 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 |
|---|---|---|---|---|
| aikunyi | 11 | 9 | 0 | 2 |
| Gierdong | 2 | 0 | 0 | 0 |
| 2dreams8 | 2 | 0 | 0 | 2 |
| xinyyhu | 1 | 0 | 0 | 0 |
| linbingkong | 1 | 0 | 0 | 0 |
| cooker-coder | 1 | 0 | 0 | 0 |
| Mineminen | 1 | 0 | 0 | 0 |
| wbzhang233 | 1 | 0 | 0 | 1 |
| TaySwiftieTay | 1 | 0 | 0 | 1 |
| wangty537 | 1 | 0 | 0 | 0 |
| zhujiayi18161778290 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#10cooker-coder2025-07-28 13:35memory usage
- Issue#9zhujiayi181617782902025-06-20 09:33Could you provide the specific code for the Visualization of Frequency Filters? Section C.5 only describes the method but does not include the detailed code.
- Issue#8Mineminen2025-04-27 12:34How to get Figure 1
- Issue#7Gierdong2025-01-14 02:23The Implementation Problem of Convolution Theory
- Issue#7Gierdong2025-01-13 05:08The Implementation Problem of Convolution Theory
- Issue#6xinyyhu2024-12-25 03:51How to explain "Transformer-based approaches tend to attenuate high-frequency components and preserve low-frequency information" in "Visualization of Frequency Filters"
- Issue comment#12dreams82024-12-18 05:19error
- Issue comment#4wbzhang2332024-12-13 02:51How to play a short term forecasting experiment with exchange_rate dataset?
- Issue comment#4TaySwiftieTay2024-12-12 06:26How to play a short term forecasting experiment with exchange_rate dataset?
- Issue comment#1aikunyi2024-12-11 07:16error
- Issue comment#3aikunyi2024-12-11 07:12in paifilter code: torch.fft.rfft(x, dim=1, norm='ortho') is on seq_len , but texfilter code torch.fft.rfft is calculated on feature_num ?
- Issue#3wangty5372024-12-06 07:07in paifilter code: torch.fft.rfft(x, dim=1, norm='ortho') is on seq_len , but texfilter code torch.fft.rfft is calculated on feature_num ?
- Issue comment#12dreams82024-12-06 03:23error
- Issue#2linbingkong2024-12-03 03:16Visualization of Frequency Filters
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 107 stars here means stars gained during the window, not the repo's star count.