Few-Shot Learning with Graph Neural Networks

Victor Garcia, Joan Bruna

11/10/2017

stat.MLcs.LG

Official code: vgsatorras/few-shot-gnn (573 stars, last commit 2023-03-01).

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.

View on arXiv View PDF

Code Implementations(1)

vgsatorras/few-shot-gnnOfficial100%

573150PythonNov 9, 20173 years ago

Similar Papers

Edge-labeling Graph Neural Network for Few-shot Learning

84% match1 repo2742019

Learning Structure-From-Motion with Graph Attention Networks

83% match1 repo272023

BAED: a New Paradigm for Few-shot Graph Learning with Explanation in the Loop

83% match2026

Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph

82% match1 repo562019

A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt Learning

82% match1 repo252024

GSHOT: Few-shot Generative Modeling of Labeled Graphs

82% match2023

Cite this paper

@article{garcia2017fewshot,
  title  = {Few-Shot Learning with Graph Neural Networks},
  author = {Victor Garcia and Joan Bruna},
  year   = {2017},
  eprint = {1711.04043},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1711.04043}
}

Add a badge to your README

Shows whether official code is linked for this paper.

[![Code of Paper](https://codeofpaper.com/badge/1711.04043.svg)](https://codeofpaper.com/paper/1711.04043)