ContinualAI / ContinualAI/avalanche
Add a plugin to manage the weight importance computation and penalization to the loss
Open
Feature - Low Priority
Training
- Dominant language
- Python
- Stars
- 2.1k
- Forks
- 321
- PR merge metrics
- No merged PRs in 30d
Description
By using a separate plugin to compute importances and penalize the loss we can reuse the same interface for EWC, MAS, SI and all future strategies.
Contributor guide
Research direction
Start by mapping the existing EWC, MAS, and SI strategies and how they currently compute importances and penalize the loss; the issue names no files or tests. Design a shared plugin interface that supports those strategies and future ones, then verify that each named strategy still works through its existing behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100