Few-Shot Learning with Graph Neural Networks

Code

• github.com/vgsatorras/few-shot-gnn
  OfficialIn paperpytorch★ 0
• github.com/HoganZhang/few-shot-gnn
  pytorch★ 2
• github.com/suvarna-kadam/Oct2018_Demo
  pytorch★ 0
• github.com/xxxnhb/few-shot-gnn
  pytorch★ 0
• github.com/Lieberk/Paddle-FSL-GNN
  paddle★ 0
• github.com/louis2889184/gnn_few_shot_cifar100
  pytorch★ 0

Abstract

We propose to study the problem of few-shot learning with the prism of inference on a partially observed graphical model, constructed from a collection of input images whose label can be either observed or not. By assimilating generic message-passing inference algorithms with their neural-network counterparts, we define a graph neural network architecture that generalizes several of the recently proposed few-shot learning models. Besides providing improved numerical performance, our framework is easily extended to variants of few-shot learning, such as semi-supervised or active learning, demonstrating the ability of graph-based models to operate well on 'relational' tasks.

Tasks

Benchmark Results

Reproductions