Browse > Methodology > Meta-Learning

Meta-Learning

106 papers with code · Methodology

Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.

State-of-the-art leaderboards

You can find evaluation results in the subtasks. You can also submitting evaluation metrics for this task.

Latest papers with code

Few-shot Text Classification with Distributional Signatures

16 Aug 2019YujiaBao/Distributional-Signatures

In this paper, we explore meta-learning for few-shot text classification.

META-LEARNING RELATION CLASSIFICATION TEXT CLASSIFICATION

14
16 Aug 2019

MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks

6 Aug 2019sharpstill/MetaAdvDet

To solve such few-shot problem with the evolving attack, we propose a meta-learning based robust detection method to detect new adversarial attacks with limited examples.

ADVERSARIAL ATTACK META-LEARNING

0
06 Aug 2019

MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation

31 Jul 2019hoyeoplee/MeLU

This paper proposes a recommender system to alleviate the cold-start problem that can estimate user preferences based on only a small number of items.

META-LEARNING RECOMMENDATION SYSTEMS

4
31 Jul 2019

Learning to learn with quantum neural networks via classical neural networks

11 Jul 2019dumkar/learning-to-learn-qnn

Quantum Neural Networks (QNNs) are a promising variational learning paradigm with applications to near-term quantum processors, however they still face some significant challenges.

META-LEARNING

25
11 Jul 2019

Few-Shot Representation Learning for Out-Of-Vocabulary Words

ACL 2019 acbull/HiCE

Existing approaches for learning word embeddings often assume there are sufficient occurrences for each word in the corpus, such that the representation of words can be accurately estimated from their contexts.

LEARNING WORD EMBEDDINGS META-LEARNING

14
01 Jul 2019

Two-stage Optimization for Machine Learning Workflow

1 Jul 2019aquemy/DPSO_experiments

For a broader adoption and scalability of machine learning systems, the construction and configuration of machine learning workflow need to gain in automation.

AUTOML META-LEARNING

0
01 Jul 2019

A meta-learning recommender system for hyperparameter tuning: predicting when tuning improves SVM classifiers

4 Jun 2019rgmantovani/mtlSuite

For many machine learning algorithms, predictive performance is critically affected by the hyperparameter values used to train them.

DECISION MAKING META-LEARNING RECOMMENDATION SYSTEMS

3
04 Jun 2019

Sequential Scenario-Specific Meta Learner for Online Recommendation

2 Jun 2019THUDM/ScenarioMeta

Our approach is based on the insight that having a good generalization from a few examples relies on both a generic model initialization and an effective strategy for adapting this model to newly arising tasks.

FEW-SHOT LEARNING META-LEARNING

23
02 Jun 2019

Meta-Learning With Differentiable Convex Optimization

CVPR 2019 kjunelee/MetaOptNet

We propose to use these predictors as base learners to learn representations for few-shot learning and show they offer better tradeoffs between feature size and performance across a range of few-shot recognition benchmarks.

FEW-SHOT IMAGE CLASSIFICATION FEW-SHOT LEARNING

182
01 Jun 2019

Meta-Learning Representations for Continual Learning

29 May 2019Khurramjaved96/mrcl

Finally, we demonstrate that a basic online updating strategy with our learned representation is competitive with rehearsal based methods for continual learning.

META-LEARNING

30
29 May 2019