AI Paper Atlas

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

DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning

Hyounguk Shon, Janghyeon Lee, Seung Hwan Kim, Junmo Kim

ECCV 2022 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation · 16 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 linearization and MSE loss (ablation)K-FAC regularization · Seq-CIFAR-100 data-IL (10 tasks)final accuracy: 79.23 -> 81.95Improved
add linearization and MSE loss (ablation)K-FAC regularization · Seq-CIFAR-100 data-IL (100 tasks)final accuracy: 73.51 -> 75.92Improved
add linearization and MSE loss (ablation)K-FAC regularization · Seq-CIFAR-100 class-IL (10 tasks)accuracy: 44.93 -> 59.86Improved
add linearization and MSE loss (ablation)TK-FAC regularization · Seq-CIFAR-100 data-IL (10 tasks)final accuracy: 79.58 -> 82.70Improved
add linearization and MSE loss (ablation)TK-FAC regularization · Seq-CIFAR-100 data-IL (100 tasks)final accuracy: 73.18 -> 80.07Improved
add linearization and MSE loss (ablation)TK-FAC regularization · Seq-CIFAR-100 class-IL (10 tasks)accuracy: 44.66 -> 59.98Improved
use TK-FAC instead of K-FAC curvature on nonlinear network with SCE (ablation)nonlinear + SCE · Seq-CIFAR-100 data-IL (10 tasks)final accuracy: 79.23 -> 79.58No clear effect
use TK-FAC instead of K-FAC curvature on linearized MSE network (ablation)DLCFT · Seq-CIFAR-100 data-IL (100 tasks)final accuracy: 75.92 -> 80.07Improved
use linearized MSE model with diagonal EWC curvature instead of nonlinear SCE (ablation)EWC · Seq-CIFAR-100 data-IL (10 tasks)final accuracy: 78.88 -> 82.17Improved
add DLCFT regularization compared with no regularizationfine-tuned ResNet-18 · Seq-CIFAR-100 data-IL (100 tasks)final accuracy: 71.83 -> 80.07Improved
add LwF regularization compared with no regularizationfine-tuned ResNet-18 · Seq-CIFAR-100 data-IL (100 tasks)final accuracy: 71.83 -> 70.95Hurt
add MAS regularization compared with no regularizationfine-tuned ResNet-18 · Seq-CIFAR-100 data-IL (100 tasks)final accuracy: 71.83 -> 52.50Hurt

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