Browse SoTA > Methodology > Meta-Learning > Few-Shot Learning

Few-Shot Learning

169 papers with code ยท Methodology
Subtask of Meta-Learning

Leaderboards

Latest papers without code

Few-Shot One-Class Classification via Meta-Learning

ICLR 2020

Our experiments on eight datasets from the image and time-series domains show that our method leads to higher results than classical OCC and few-shot classification approaches, and demonstrate the ability to learn unseen tasks from only few normal class samples.

FEW-SHOT LEARNING TIME SERIES

Online probabilistic label trees

8 Jul 2020

We introduce online probabilistic label trees (OPLTs), an algorithm that trains a label tree classifier in a fully online manner, without any prior knowledge about the number of training instances, their features and labels.

FEW-SHOT LEARNING MULTI-CLASS CLASSIFICATION

Meta-Learning with Network Pruning

7 Jul 2020

To remedy this deficiency, we propose a network pruning based meta-learning approach for overfitting reduction via explicitly controlling the capacity of network.

FEW-SHOT LEARNING NETWORK PRUNING

Covariate Distribution Aware Meta-learning

6 Jul 2020

We begin by introducing a graphical model that explicitly leverages very few samples drawn from p(x) to better infer the posterior over the optimal parameters of the conditional distribution (p(y|x)) for each task.

FEW-SHOT LEARNING

Meta-Learning for Variational Inference

ICLR 2020

Variational inference (VI) plays an essential role in approximate Bayesian inference due to its computational efficiency and broad applicability.

BAYESIAN INFERENCE FEW-SHOT LEARNING IMAGE GENERATION RECOMMENDATION SYSTEMS

Learning to learn generative programs with Memoised Wake-Sleep

6 Jul 2020

We study a class of neuro-symbolic generative models in which neural networks are used both for inference and as priors over symbolic, data-generating programs.

FEW-SHOT LEARNING

MetaConcept: Learn to Abstract via Concept Graph for Weakly-Supervised Few-Shot Learning

5 Jul 2020

To this end, we propose a novel meta-learning framework, called MetaConcept, which learns to abstract concepts via the concept graph.

FEW-SHOT LEARNING

A Revision of Neural Tangent Kernel-based Approaches for Neural Networks

2 Jul 2020

(2) A generalization error bound invariant of network size was derived by using a data-dependent complexity measure (CMD).

FEW-SHOT LEARNING

Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations

ACL 2020

We introduce Span-ConveRT, a light-weight model for dialog slot-filling which frames the task as a turn-based span extraction task.

FEW-SHOT LEARNING SLOT FILLING