AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Transferring Knowledge across Learning Processes

Sebastian Flennerhag, Pablo G. Moreno, Neil D. Lawrence, Andreas Damianou

ICLR 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Meta-augmentation and meta-objectives · 38 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
Use Leap instead of Reptilemeta-learning across Omniglot alphabets · Omniglot held-out tasks, 25 pretraining taskstest error: 29.4 -> 24.8Improved
Use a loss-surface task manifold instead of parameter space alone (ablation)Leap · Omniglotprediction errorImproved
Use gradient-path length rather than gradient-path energy (ablation)Leap · OmniglotperformanceImproved
Add the stabilizer to the meta objective (ablation)Leap · Omniglotconvergence speedImproved
Remove the stabilizer (ablation)Leap · Omniglotconvergence speedHurt
Use parameter space alone and gradient-path energy, as in the Reptile-like configuration (ablation)Leap · OmniglotperformanceHurt
Use only one epoch of task training during meta-training (ablation)Leap · Multi-CVperformanceNo clear effect

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