SOTAVerified

Meta-Learning

Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.

( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1321–1330 of 3569 papers

TitleStatusHype
Interval Bound Interpolation for Few-shot Learning with Few TasksCode0
Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model CompressionCode0
Improving Memory Efficiency for Training KANs via Meta LearningCode0
Centroids Matching: an efficient Continual Learning approach operating in the embedding spaceCode0
Improving Meta-Continual Learning Representations with Representation ReplayCode0
Improving Generalization in Meta-Learning via Meta-Gradient AugmentationCode0
Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-TimeCode0
Improving Meta-Learning Generalization with Activation-Based Early-StoppingCode0
A Neural-Symbolic Architecture for Inverse Graphics Improved by Lifelong Meta-LearningCode0
Fast Unsupervised Deep Outlier Model Selection with HypernetworksCode0
Show:102550
← PrevPage 133 of 357Next →
All datasetsML10MT50ML45OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-train success rate97.8—Unverified
2MZMeta-train success rate97.6—Unverified
3MAMLMeta-test success rate36—Unverified
4RL^2Meta-test success rate10—Unverified
5DnCMeta-test success rate5.4—Unverified
6PEARLMeta-test success rate0—Unverified
#ModelMetricClaimedVerifiedStatus
1SoftModuleAverage Success Rate60—Unverified
2Multi-task multi-head SACAverage Success Rate35.85—Unverified
3DisCorAverage Success Rate26—Unverified
4NDPAverage Success Rate11—Unverified
#ModelMetricClaimedVerifiedStatus
1MZ+ReconMeta-test success rate (zero-shot)18.5—Unverified
2MZMeta-test success rate (zero-shot)17.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Metadrop% Test Accuracy95.75—Unverified