AI Paper Atlas

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

Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning

Xinyuan Gao, Songlin Dong, Yuhang He, Qiang Wang, Yihong Gong

ECCV 2024 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation · 27 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
add the scale-and-shift (S&S) module before incremental training (ablation)C-ADA · ImageNet-R (P=10)A_N: 0.73% drop when removedImproved
add the orthogonal loss between new and old CAL weights (ablation)C-ADA · ImageNet-R (P=10)A_N: 3.76% drop when removedImproved
add the continual adapter layer (CAL) instead of tuning only the classifier (ablation)C-ADA · ImageNet-R (P=10)A_N: 7.72% drop when removedImproved
replace key-query-matched prompts with an adapter without matching (single forward pass)C-ADA vs CODA-P-S · ImageNet-R (P=10)A_N: 73.93 -> 76.66Improved
attach CAL to shallow layers 0-5 instead of deep layers 6-11 (ablation)C-ADA · ImageNet-R (P=10)A_N: 72.51 -> 76.21Improved
attach CAL to layers 0-4 instead of all 12 layers (ablation)C-ADA · ImageNet-R (P=10)A_N: 75.23 -> 76.66Improved
attach CAL to projection layer instead of QKV attention layer (ablation)C-ADA · ImageNet-R (P=10)A_N: 76.04 -> 76.25Improved
attach CAL to both Proj and MLP instead of a single position (ablation)C-ADA · ImageNet-R (P=10)A_N: 76.25 -> 76.66Improved
vary the split of middle dimensions between Proj and MLP CALs (ablation)C-ADA · ImageNet-R (P=10)A_N: 76.51 to 76.66No clear effect
increase trainable parameters (middle dimension of CAL) (ablation)C-ADA · ImageNet-R (P=20)A_N: more parameters give higher accuracy; 0.35% params gives 71.92Improved
use C-ADA instead of S-Prompts on domain-incremental benchmarksC-ADA · CORe50A_N: 83.13 -> 89.45Improved
use C-ADA instead of CODA for forgetting on ImageNet-R P=20C-ADA · ImageNet-R (P=20)F_N: 1.00 (CODA) vs 1.02 (C-ADA)No clear effect

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