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 1201–1250 of 3569 papers

TitleStatusHype
Instance-Conditional Timescales of Decay for Non-Stationary Learning—0
Transductive Linear Probing: A Novel Framework for Few-Shot Node ClassificationCode1
Task-Adaptive Meta-Learning Framework for Advancing Spatial GeneralizabilityCode0
Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive LearningCode1
General-Purpose In-Context Learning by Meta-Learning TransformersCode0
Learning Domain Invariant Prompt for Vision-Language ModelsCode1
Learn to Explore: on Bootstrapping Interactive Data Exploration with Meta-learning—0
Few-Shot Preference Learning for Human-in-the-Loop RL—0
Domain-General Crowd Counting in Unseen ScenariosCode1
DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization—0
Meta-Learning Fast Weight Language Models—0
Meta Learning for Few-Shot Medical Text Classification—0
Meta-Shop: Improving Item Advertisement For Small Businesses—0
Adaptive Robust Model Predictive Control via Uncertainty Cancellation—0
On the Energy and Communication Efficiency Tradeoffs in Federated and Multi-Task Learning—0
Towards Cross Domain Generalization of Hamiltonian Representation via Meta Learning—0
Generalized Face Anti-Spoofing via Multi-Task Learning and One-Side Meta Triplet Loss—0
Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning—0
Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection—0
Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation ModelsCode1
Multi-Modal Few-Shot Temporal Action DetectionCode1
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task LearningCode0
Meta-Learning the Inductive Biases of Simple Neural CircuitsCode0
Meta-Learning for Automated Selection of Anomaly Detectors for Semi-Supervised Datasets—0
Learning to Rasterize DifferentiablyCode0
Generalizable Implicit Neural Representations via Instance Pattern ComposersCode1
Adversarial Attacks are a Surprisingly Strong Baseline for Poisoning Few-Shot Meta-Learners—0
Dynamic Loss For Robust LearningCode0
A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms—0
Discovering Evolution Strategies via Meta-Black-Box OptimizationCode2
Adversarial Cheap TalkCode3
Environmental Sensor Placement with Convolutional Gaussian Neural ProcessesCode0
Audio Anti-spoofing Using a Simple Attention Module and Joint Optimization Based on Additive Angular Margin Loss and Meta-learning—0
NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision ResearchCode1
Latent Bottlenecked Attentive Neural ProcessesCode0
Artificial intelligence approaches for materials-by-design of energetic materials: state-of-the-art, challenges, and future directions—0
Few-Shot Inductive Learning on Temporal Knowledge Graphs using Concept-Aware Information—0
Meta-Learning of Neural State-Space Models Using Data From Similar Systems—0
Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice—0
Towards Generalization on Real Domain for Single Image Dehazing via Meta-Learning—0
Few-shot Metric Learning: Online Adaptation of Embedding for Retrieval—0
Stackelberg Meta-Learning Based Control for Guided Cooperative LQG Systems—0
Cross-Platform and Cross-Domain Abusive Language Detection with Supervised Contrastive Learning—0
Few-shot Classification with Hypersphere Modeling of Prototypes—0
Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-MindCode0
MetaLoc: Learning to Learn Wireless Localization—0
Learning advisor networks for noisy image classificationCode0
Enabling Deep Learning-based Physical-layer Secret Key Generation for FDD-OFDM Systems in Multi-Environments—0
Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot LearningCode1
Toward Unsupervised Outlier Model SelectionCode1
Show:102550
← PrevPage 25 of 72Next →
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