AI Paper Atlas

Research map / Continual learning / Online and replay-based

Exploring Example Influence in Continual Learning

Qing Sun, Fan Lyu, Fanhua Shang, Wei Feng, Liang Wan

NeurIPS 2022 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 15 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 influence-based rehearsal selection (RehSel) over random selection (ablation)MetaSP · Split CIFAR-10 class-incremental, buffer 500final accuracy A_inf: 49.16 -> 50.10Improved
add RehSel (ablation)MetaSP · Split CIFAR-100 class-incremental, buffer 500final accuracy A_inf: 18.96 -> 19.28Improved
add RehSel (ablation)MetaSP · Split CIFAR-10 class-incremental, buffer 500first accuracy A_1 / A_m: 96.82 -> 96.81 (A_1)Mixed
remove K-means clustering from rehearsal selection (ablation)RehSel · Split CIFAR-10 class-incrementalfinal accuracy A_inf: 50.10 -> 38.50Hurt
remove influence ranking, cluster only (ablation)RehSel · Split CIFAR-10 class-incrementalfinal accuracy A_inf: 50.10 -> 47.55Hurt
use only stability-aware or only plasticity-aware influence instead of fused (ablation)MetaSP · Split CIFAR-10first/final accuracyMixed
use more pseudo-update iterations (ablation)MetaSP · Split CIFAR-10accuracyImproved
larger SP validation set (ablation)MetaSP · Split CIFAR-10/100accuracyImproved
apply MetaSP vs ER baselineER · Split CIFAR-10 class-incremental, buffer 500final accuracy A_inf: 40.45 -> 49.16Improved
apply MetaSP vs best baselineGMED · Split Mini-Imagenet task-incremental, buffer 500final accuracy A_inf: 30.47 -> 32.59Improved
MetaSP influence approximation vs Neumann seriesinfluence estimation · 1000 examplestrue positives: 642 -> 650Improved

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