Skip to content

Official implementation of the paper "FilterNet: Harnessing Frequency Filters for Time Series Forecasting"

active 2024-11-032026-03-11 (UTC)

Partial coverage20,513 / 26,269 hourly files (78%) · 2 absent upstream · 5,753 failed, retryable2023-08-152026-08-13 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
148
Pushes
9
Pull requests
0
Issues
8
Stars
107
Forks
11

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

ContributorContributionsPushesPRsComments
aikunyi11902
Gierdong2000
2dreams82002
xinyyhu1000
linbingkong1000
cooker-coder1000
Mineminen1000
wbzhang2331001
TaySwiftieTay1001
wangty5371000
zhujiayi181617782901000

Recent activity

Latest issues, pull requests and releases

  • Issue#10cooker-coder2025-07-28 13:35
    memory usage
  • Issue#9zhujiayi181617782902025-06-20 09:33
    Could 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 12:34
    How to get Figure 1
  • Issue#7Gierdong2025-01-14 02:23
    The Implementation Problem of Convolution Theory
  • Issue#7Gierdong2025-01-13 05:08
    The Implementation Problem of Convolution Theory
  • Issue#6xinyyhu2024-12-25 03:51
    How 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 05:19
    error
  • Issue comment#4wbzhang2332024-12-13 02:51
    How to play a short term forecasting experiment with exchange_rate dataset?
  • Issue comment#4TaySwiftieTay2024-12-12 06:26
    How to play a short term forecasting experiment with exchange_rate dataset?
  • Issue comment#1aikunyi2024-12-11 07:16
    error
  • Issue comment#3aikunyi2024-12-11 07:12
    in 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 07:07
    in 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 03:23
    error
  • Issue#2linbingkong2024-12-03 03:16
    Visualization 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.