AI Paper Atlas

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

Compositional generalization through meta sequence-to-sequence learning

Brenden M Lake

NeurIPS 2019 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Meta-augmentation and meta-objectives · 43 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
Train across episodes of changing sequence-to-sequence mappings and use a support memoryMeta seq2seq · SCAN add jumptest accuracy: 0.03% -> 99.95%Improved
Train across episodes of changing sequence-to-sequence mappings and use a support memoryMeta seq2seq · SCAN around righttest accuracy: 0.0% -> 99.96%Improved
Train across episodes of changing sequence-to-sequence mappings and use a support memoryMeta seq2seq · SCAN lengthtest accuracy: 7.71% -> 16.64%Improved
Add support loss during meta-training (ablation)Meta seq2seq · SCAN add jumptest accuracy: 5.43% -> 99.95%Improved
Add support loss during meta-training (ablation)Meta seq2seq · SCAN add jump, augmentation meta-trainingtest accuracy: 99.48% -> 98.71%No clear effect
Add decoder attention over query context (ablation)Meta seq2seq · SCAN add jumptest accuracy: 10.32% -> 99.95%Improved
Add decoder attention over query context (ablation)Meta seq2seq · SCAN add jump, augmentation meta-trainingtest accuracy: 9.29% -> 98.71%Improved
Augment training with additional primitivesStandard seq2seq · SCAN add jumptest accuracy: 0.03% -> 12.26%Improved
Use meta-training rather than standard trainingMeta seq2seq · SCAN add jump, augmentation meta-trainingtest accuracy: 12.26% -> 98.71%Improved
Use meta-training rather than standard trainingMeta seq2seq · Mutual exclusivityaccuracy: 100%Improved
Use meta-training rather than standard trainingMeta seq2seq · SCAN around righttest accuracy: 0.0% -> 99.96%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