AI Paper Atlas

Research map / Continual learning / Online and replay-based

Detect, Decide, Unlearn: A Transfer-Aware Framework for Continual Learning

Yiwen Wang, Diana Benavides-Prado, Yun Sing Koh

ICLR 2026 · Continual learning › Online and replay-based · approach: Theoretical analysis of forgetting

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 DEDUCE (gradient-conflict detection)DER++ · CIFAR-100 CILACC (%): 36.8 -> 39.8Improved
add DEDUCE (gradient-conflict detection)HAL · CIFAR-100 CILACC (%): 11.6 -> 24.8Improved
add DEDUCE (gradient-conflict detection)DER++ · Tiny-ImageNet CILACC (%): 15.6 -> 22.1Improved
use gradient-conflict detection instead of transferability bound (ablation)DEDUCE on DER++ · CIFAR-100 CILACC (%): 37.8 -> 39.8Improved
add Local Unlearning Module (ablation)DER++ · CIFAR-100 CILACC (%): 36.8 -> 39.4Improved
add Global Unlearning Module (ablation)DER++ · CIFAR-100 CILACC (%): 36.8 -> 37.7Improved
add GUM only versus full DEDUCE (ablation)DER++ · CORE-50 CILACC (%): 41.2 -> 42.1Mixed
add FIM regularizer Lreg (ablation)DEDUCE on DER++ · Tiny-ImageNet CILACC (%): 19.6 -> 22.1Improved
raise local unlearning rate delta from 0.0001 to 0.01 (0.05 degrades) (ablation)DEDUCE on DER++ · CIFAR-100 CILACC (%): 37.77 -> 44.08 -> 31.04Mixed
raise global unlearning rate phi from 1e-5 to 5e-4 (ablation)DEDUCE on DER++ · CIFAR-100 CILACC (%): 39.84 -> 31.26Hurt
stricter trigger tolerance epsilon -0.2 instead of 0.0 (ablation)DEDUCE on DER++ · CIFAR-100 CILACC (%): 39.84 -> 35.97Hurt
add DEDUCE at small buffer size 100 (ablation)ER · CIFAR-100 buffer 100ACC (%): 58.23 -> 62.65Improved

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