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 1101–1110 of 3569 papers

TitleStatusHype
A Primal-Dual Subgradient Approachfor Fair Meta LearningCode0
Constrained Meta-Reinforcement Learning for Adaptable Safety Guarantee with Differentiable Convex ProgrammingCode0
Joint Optimization of Class-Specific Training- and Test-Time Data Augmentation in SegmentationCode0
Joint inference and input optimization in equilibrium networksCode0
Consistency of Compositional Generalization across Multiple LevelsCode0
It HAS to be Subjective: Human Annotator Simulation via Zero-shot Density EstimationCode0
Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model CompressionCode0
Layer-compensated Pruning for Resource-constrained Convolutional Neural NetworksCode0
Interval Bound Interpolation for Few-shot Learning with Few TasksCode0
Approximately Equivariant Neural ProcessesCode0
Show:102550
← PrevPage 111 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