Open
Conversation
Collaborator
|
Hi, sorry for the late reply. The code looks ok. Did you reproduce the paper experiments? I'm not familiar with the paper so I can't evaluate if your implementation matches the paper exactly at the moment. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I Implemented the SER (Strong Experience Replay) algorithm from the paper "Continual Learning with Strong Experience Replay" https://arxiv.org/pdf/2302.11346 .
It is a modified version of DER++, so my implementation of SER is strongly based on the DER++ implementation here on avalanche.
I plan to create a PR on continual-learning-baselines when I will be able to replicate the paper results.
On my partial experiments so far SER outperforms DER++ on the SMNIST and CIFAR10 benchmarks in a class incremental setup.