AI Paper Atlas

Research map / Continual learning / Continual fine-tuning of LLMs

SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model

Gengwei Zhang, Liyuan Wang, Guoliang Kang, Ling Chen, Yunchao Wei

ICCV 2023 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation · 155 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use a small learning rate (0.0001) for the representation layer and 0.01 for the classifier (Slow Learner) (ablation)Seq FT · Split CIFAR-100 (IN21K-Sup)Last-Acc (%): 41.77 -> 88.86Improved
use the slow learner on a hard out-of-distribution benchmark (ablation)Seq FT · Split ImageNet-R (IN21K-Sup)Last-Acc (%): 26.95 -> 71.80Improved
update the representation layer with slow learner instead of freezing it (ablation)Seq FT · Split CIFAR-100 (IN21K-Sup)Last-Acc (%): 63.75 -> 88.86Improved
add classifier alignment with logit normalization on top of slow learner (ablation)SLCA · Split CUB-200 (IN21K-Sup)Last-Acc (%): 68.07 -> 84.71Improved
add classifier alignment with logit normalization on top of slow learner (ablation)SLCA · Split Cars-196 (IN21K-Sup)Last-Acc (%): 49.74 -> 67.73Improved
add logit normalization to classifier alignment (ablation)SLCA · Split ImageNet-R (IN21K-Sup)Last-Acc (%): 74.41 -> 77.00Improved
add logit normalization to classifier alignment (ablation)SLCA · Split Cars-196 (IN21K-Sup)Last-Acc (%): 67.90 -> 67.73No clear effect
align classifier during representation learning instead of post-hoc (ablation)SLCA · Split CIFAR-100Last-Acc (%): worsen by 27.89%Hurt
add classifier alignment to a fixed representation layer (ablation)Fixed representation layer · Split CUB-200 (IN21K-Sup)Last-Acc (%): 60.44 -> 82.71Improved
lower the representation learning rate too far (0.001 vs 0.0001) (ablation)Seq FT · Split Cars-196 (IN21K-Sup)Last-Acc (%): 49.74 -> 15.74 at lr 0.001Hurt
add classifier alignment to BiC with slow learner (ablation)BiC · Split ImageNet-R (IN21K-Sup)Last-Acc (%): 64.89 -> 74.49Improved
add classifier alignment to EWC with slow learner (ablation)EWC · Split CIFAR-100 (IN21K-Sup)Last-Acc (%): 89.30 -> 90.61Improved

Later papers that compared with this method

22 later accepted papers report SLCA as a baseline in their results tables; 21 of them report a better number on most of the results they share with it.

14 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy