AI Paper Atlas

Research map / Continual learning / Online and replay-based

Meta-Learning Representations for Continual Learning

Khurram Javed, Martha White

NeurIPS 2019 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 25 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
replace Pre-training representation with OML representation for online SGD (ablation)Online SGD · Split-Omniglot 50 tasksaccuracy (%): 21.16 -> 64.72Improved
learn from OML representations instead of standard networkMER · Split-Omniglot 50 tasksaccuracy (%): 54.88 -> 76.00Improved
learn from OML representations instead of standard networkER-Reservoir · Split-Omniglot 20 tasksaccuracy (%): 24.32 -> 60.92Improved
learn from OML representations instead of standard networkEWC · Split-Omniglot 50 tasksaccuracy (%): 05.08 -> 64.44Improved
use fixed Pre-training representation instead of standard networkMER · Split-Omniglot 20 tasksaccuracy (%): 29.02 -> 42.05Improved
use fixed Pre-training representation instead of standard networkApprox IID · Split-Omniglot 20 tasksaccuracy (%): 48.02 -> 46.02No clear effect
OML with plain online SGD versus other continual methods on standard networksOML + Online SGD · Split-Omniglot 50 tasksaccuracy (%): 64.72 vs 54.88 (standard MER)Improved
OML objective versus MAML-Rep (adds online-aware interference minimization) (ablation)representation meta-learning · Split-Omniglot onlineaccuracyImproved
learn a representation encoder instead of only a model initialization (ablation)OML · Incremental sine wavestraining error at meta-testImproved
OML versus Pre-training representation instance sparsityrepresentation · Omniglot training setinstance sparsity (% active): 38% -> 3.8%Improved

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