Recent few-shot meta-learning papers

Siamese Neural Networks for One-shot Image Recognition (Siamense)
Matching networks for one shot learning (Matching networks)
Prototypical Networks for Few-shot Learning (Prototypical)
Gaussian Prototypical Networks for Few-Shot Learning on Omniglot (Gaussian Prototypical)
Meta-Learning for Semi-Supervised Few-Shot Classification (semi-prototypical)
Learning to Compare: Relation Network for Few-Shot Learning (Compare)
Few-Shot Learning Through an Information Retrieval Lens
Meta-Learning with Temporal Convolutions (TCML)
A Simple Neural Attentive Meta-Learner (SNAIL)
Attentive Recurrent Comparators
Few-Shot Learning with Metric-Agnostic Conditional Embeddings

Optimization as a model for few-shot learning (Meta-LSTM)
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (MAML)
SEMI-SUPERVISED FEW-SHOT LEARNING WITH MAML (semi-MAML)
META-LEARNING AND UNIVERSALITY: DEEP REPRESENTATIONS AND GRADIENT DESCENT CAN APPROXIMATE ANY LEARNING ALGORITHM (Uncertainty-MAML)
RECASTING GRADIENT-BASED META-LEARNING AS HIERARCHICAL BAYES (Bayes-MAML)
Semi-Supervised Few-Shot Learning with MAML (semi-MAML)
Meta-SGD: Learning to Learn Quickly for Few-Shot Learning (Meta-SGD)
Deep Meta-Learning: Learning to Learn in the Concept Space (DEML)
On First-Order Meta-Learning Algorithms
Meta Networks
Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace

LEARNING TO REMEMBER RARE EVENTS
Few-Shot Object Recognition from Machine-Labeled Web Images
Meta-Learning with Memory-Augmented Neural Networks

FAST ADAPTATION IN GENERATIVE MODELS WITH GENERATIVE MATCHING NETWORKS
Generative Adversarial Residual Pairwise Networks for One Shot Learning (GAN)
FEW-SHOT AUTOREGRESSIVE DENSITY ESTIMATION: TOWARDS LEARNING TO LEARN DISTRIBUTIONS (density-MAML)
Low-Shot Learning from Imaginary Data
A Generative Approach to Zero-Shot and Few-Shot Action Recognition

One-Shot Learning in Discriminative Neural Networks
Discriminative k-shot learning using probabilistic models
Learning to Warm-Start Bayesian Hyperparameter Optimization
A Bridge Between Hyperparameter Optimization and Larning-to-learn
Combinets: Learning New Classifiers via Recombination

Learning to Model the Tail
Learning from Small Sample Sets by Combining Unsupervised Meta-Training with CNNs
Fine-grained recognition of thousands of object categories with single-example training
Learning Unsupervised Learning Rules
Few-Shot Learning with Graph Neural Networks
Transfer Learning in a Transductive Setting
Few-shot Learning by Exploiting Visual Concepts within CNNs
Learning Transferrable Representations for Unsupervised Domain Adaptation