Browse SoTA > Methodology > Meta-Learning

Meta-Learning

273 papers with code · Methodology

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 )

Benchmarks

Latest papers with code

One Model, Many Languages: Meta-learning for Multilingual Text-to-Speech

3 Aug 2020Tomiinek/Multilingual_Text_to_Speech

We introduce an approach to multilingual speech synthesis which uses the meta-learning concept of contextual parameter generation and produces natural-sounding multilingual speech using more languages and less training data than previous approaches.

META-LEARNING SPEECH SYNTHESIS

98
03 Aug 2020

Few-shot Scene-adaptive Anomaly Detection

15 Jul 2020yiweilu3/Few-shot-Scene-adaptive-Anomaly-Detection

In this paper, we propose a novel few-shot scene-adaptive anomaly detection problem to address the limitations of previous approaches.

ANOMALY DETECTION META-LEARNING

9
15 Jul 2020

Non-greedy Gradient-based Hyperparameter Optimization Over Long Horizons

15 Jul 2020polo5/NonGreedyGradientHPO

On CIFAR-10 we match the baseline performance, and demonstrate for the first time that learning rate, momentum and weight decay schedules can be learned with gradients on a dataset of this size.

HYPERPARAMETER OPTIMIZATION META-LEARNING

3
15 Jul 2020

Concept Learners for Generalizable Few-Shot Learning

14 Jul 2020snap-stanford/comet

Developing algorithms that are able to generalize to a novel task given only a few labeled examples represents a fundamental challenge in closing the gap between machine- and human-level performance.

FEW-SHOT LEARNING IMAGE CLASSIFICATION

6
14 Jul 2020

Auto-Sklearn 2.0: The Next Generation

8 Jul 2020automl/auto-sklearn

In this paper we introduce new Automated Machine Learning (AutoML) techniques motivated by our winning submission to the second ChaLearn AutoML challenge, PoSH Auto-sklearn.

AUTOML META-LEARNING

4,742
08 Jul 2020

MAMO: Memory-Augmented Meta-Optimization for Cold-start Recommendation

7 Jul 2020dongmanqing/Code-for-MAMO

However, most meta-learning based recommendation approaches adopt model-agnostic meta-learning for parameter initialization, where the global sharing parameter may lead the model into local optima for some users.

META-LEARNING RECOMMENDATION SYSTEMS

0
07 Jul 2020

Meta-Learning Symmetries by Reparameterization

6 Jul 2020facebookresearch/higher

Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers are equivariant to shifts of the input.

META-LEARNING

847
06 Jul 2020

Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs

5 Jul 2020DeepGraphLearning/FewShotRE

To more effectively generalize to new relations, in this paper we study the relationships between different relations and propose to leverage a global relation graph.

META-LEARNING RELATION EXTRACTION

8
05 Jul 2020

Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains

4 Jul 2020liuquande/SAML

We present a novel shape-aware meta-learning scheme to improve the model generalization in prostate MRI segmentation.

DOMAIN GENERALIZATION META-LEARNING

21
04 Jul 2020