SOTAVerified|Agents Browse Leaderboard About

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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 201–210 of 3569 papers

Title	Date	Tasks	Status	Hype
Faster Meta Update Strategy for Noise-Robust Deep Learning	Apr 30, 2021	Deep LearningImage Classification	CodeCode Available	1
Fast Online Adaptation in Robotics through Meta-Learning Embeddings of Simulated Priors	Mar 10, 2020	Meta-LearningModel-based Reinforcement Learning	CodeCode Available	1
Few-shot Action Recognition with Prototype-centered Attentive Learning	Jan 20, 2021	Action RecognitionContrastive Learning	CodeCode Available	1
Few-shot Classification via Adaptive Attention	Aug 6, 2020	ClassificationFew-Shot Learning	CodeCode Available	1
A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings	Dec 12, 2020	Graph Representation LearningMeta-Learning	CodeCode Available	1
Amortized Probabilistic Conditioning for Optimization, Simulation and Inference	Oct 20, 2024	Bayesian OptimizationMeta-Learning	CodeCode Available	1
A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt Learning	Feb 2, 2024	Few-Shot LearningGraph Representation Learning	CodeCode Available	1
A Meta-Learning Approach for Training Explainable Graph Neural Networks	Sep 20, 2021	Graph ClassificationMeta-Learning	CodeCode Available	1
Few-Shot Learning with Class Imbalance	Jan 7, 2021	Few-Shot LearningMeta-Learning	CodeCode Available	1
ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification	May 16, 2023	ClassificationContrastive Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 21 of 357Next →

All datasets ML10 MT50 ML45 OMNIGLOT - 1-Shot, 20-way

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	MZ+Recon	Meta-train success rate	97.8	—	Unverified
2	MZ	Meta-train success rate	97.6	—	Unverified
3	MAML	Meta-test success rate	36	—	Unverified
4	RL^2	Meta-test success rate	10	—	Unverified
5	DnC	Meta-test success rate	5.4	—	Unverified
6	PEARL	Meta-test success rate	0	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SoftModule	Average Success Rate	60	—	Unverified
2	Multi-task multi-head SAC	Average Success Rate	35.85	—	Unverified
3	DisCor	Average Success Rate	26	—	Unverified
4	NDP	Average Success Rate	11	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MZ+Recon	Meta-test success rate (zero-shot)	18.5	—	Unverified
2	MZ	Meta-test success rate (zero-shot)	17.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Metadrop	% Test Accuracy	95.75	—	Unverified