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 1276–1300 of 3569 papers

TitleStatusHype
Exploring intra-task relations to improve meta-learning algorithms—0
Hybrid-Task Meta-Learning: A Graph Neural Network Approach for Scalable and Transferable Bandwidth Allocation—0
Personalized Federated Learning with Contextual Modulation and Meta-LearningCode0
Meta-Learning-Based Adaptive Stability Certificates for Dynamical SystemsCode0
Meta Transfer of Self-Supervised Knowledge: Foundation Model in Action for Post-Traumatic Epilepsy Prediction—0
AutoXPCR: Automated Multi-Objective Model Selection for Time Series ForecastingCode0
Meta-Learning with Versatile Loss Geometries for Fast Adaptation Using Mirror DescentCode0
POND: Multi-Source Time Series Domain Adaptation with Information-Aware Prompt Tuning—0
Scaling Opponent Shaping to High Dimensional Games—0
Outlier detection using flexible categorisation and interrogative agendas—0
LabelCraft: Empowering Short Video Recommendations with Automated Label CraftingCode0
Few-Shot Learning from Augmented Label-Uncertain Queries in Bongard-HOI—0
Test-Time Domain Adaptation by Learning Domain-Aware Batch NormalizationCode0
3FM: Multi-modal Meta-learning for Federated TasksCode0
Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label LearningCode0
Constrained Meta-Reinforcement Learning for Adaptable Safety Guarantee with Differentiable Convex ProgrammingCode0
Meta-learning to Calibrate Gaussian Processes with Deep Kernels for Regression Uncertainty Estimation—0
Accelerating Meta-Learning by Sharing Gradients—0
ReFusion: Learning Image Fusion from Reconstruction with Learnable Loss via Meta-Learning—0
ICL Markup: Structuring In-Context Learning using Soft-Token Tags—0
Improving the performance of weak supervision searches using transfer and meta-learning—0
RAFIC: Retrieval-Augmented Few-shot Image ClassificationCode0
Hacking Task Confounder in Meta-LearningCode0
Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link Prediction—0
On the adaptation of in-context learners for system identificationCode0
Show:102550
← PrevPage 52 of 143Next →
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