Skip to content

ContinualAI/continual-learning-baselines

View on GitHub ↗Related repositories →

Continual learning baselines and strategies from popular papers, using Avalanche. We include EWC, SI, GEM, AGEM, LwF, iCarl, GDumb, and other strategies.

active 2023-08-302026-04-18 (UTC)

Partial coverage23,943 / 26,315 hourly files (91%) · 2 absent upstream · 2,372 failed, retryable2023-08-152026-08-15 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
152
Pushes
1
Pull requests
5
Issues
17
Stars
115
Forks
10

Activity over time

Daily event counts in the loaded window

Line chart, 963 days from 2023-08-30 to 2026-04-18. Pushes: 1 total, peak 1 in a day. Pull requests: 5 total, peak 3 in a day. Issues: 17 total, peak 2 in a day. Comments: 3 total, peak 1 in a day. Stars: 115 total, peak 2 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
AndreaCossu18131
AlboAlby002011
vmromero-ubi2001
uebian1000
shahdivyank1000
AnonymousUTC81000
tachyonicClock1010
August97081000

Recent activity

Latest issues, pull requests and releases

  • Issue#88AndreaCossu2025-01-31 23:00
    Experiments failed to be reproduced
  • Issue#87AndreaCossu2024-12-31 23:00
    Experiments failed to be reproduced
  • Issue#86shahdivyank2024-12-09 13:00
    Active Learning Method for Experience Sampling
  • Pull request#85AlboAlby002024-11-25 06:28
  • Issue comment#84AlboAlby002024-11-25 06:19
    Two Different Buffers Are Used On LaMAML Strategy
  • Issue#83AndreaCossu2024-10-31 23:00
    Experiments failed to be reproduced
  • Issue#82AndreaCossu2024-09-30 22:00
    Experiments failed to be reproduced
  • Issue#81AndreaCossu2024-08-31 22:00
    Experiments failed to be reproduced
  • Issue#80AndreaCossu2024-07-31 22:00
    Experiments failed to be reproduced
  • Issue#79AndreaCossu2024-06-30 22:00
    Experiments failed to be reproduced
  • Issue#78AndreaCossu2024-05-31 22:00
    Experiments failed to be reproduced
  • Issue#76uebian2024-04-07 06:38
    Reproduce L2P result
  • Issue#75AndreaCossu2024-03-31 22:00
    Experiments failed to be reproduced
  • Issue#74vmromero-ubi2024-03-25 05:37
    Synaptic Intelligence vs Naive Finetuning Comparison
  • Issue#73AnonymousUTC82024-03-25 02:26
    One Little Typo in experiments.slipt_mnist.naive
  • Issue#68AndreaCossu2024-02-13 08:33
    Experiments failed to be reproduced
  • Issue#68AndreaCossu2024-02-13 08:33
    Experiments failed to be reproduced
  • Issue comment#66vmromero-ubi2024-02-10 05:23
    Question about Synaptic intelligence baseline on the SplitMNIST dataset
  • Issue#65August97082023-12-01 06:39
    Something wrong about import?
  • Pull request#64AndreaCossu2023-09-28 15:43
  • Pull request#64AndreaCossu2023-09-28 15:42
  • Pull request#63AndreaCossu2023-09-28 15:34
  • Issue comment#63AndreaCossu2023-09-28 10:43
    Add PackNet baseline
  • Pull request#63tachyonicClock2023-09-20 05:12
  • Issue#62AndreaCossu2023-09-02 03:55
    Experiments failed to be reproduced

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 115 stars here means stars gained during the window, not the repo's star count.