ContinualAI / ContinualAI/avalanche

Add a plugin to manage the weight importance computation and penalization to the loss

Open
#953 1 comment 0 reactions 0 assignees View on GitHub
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

Open the contributing 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.