TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Few-Shot Learning with Graph Neural Networks

Few-Shot Learning with Graph Neural Networks

Victor Garcia, Joan Bruna

2017-11-10Few-Shot LearningActive LearningCross-Domain Few-Shot
PaperPDFCodeCodeCode(official)CodeCodeCode

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.

Results

TaskDatasetMetricValueModel
Few-Shot LearningChestX5 shot25.27GNN
Few-Shot LearningEuroSAT5 shot83.64GNN
Few-Shot LearningISIC20185 shot43.94GNN
Image ClassificationStanford Dogs 5-way (5-shot)Accuracy62.27GNN++
Image ClassificationStanford Cars 5-way (5-shot)Accuracy71.25GNN++
Image ClassificationStanford Cars 5-way (1-shot)Accuracy55.85GNN++
Meta-LearningChestX5 shot25.27GNN
Meta-LearningEuroSAT5 shot83.64GNN
Meta-LearningISIC20185 shot43.94GNN
Few-Shot Image ClassificationStanford Dogs 5-way (5-shot)Accuracy62.27GNN++
Few-Shot Image ClassificationStanford Cars 5-way (5-shot)Accuracy71.25GNN++
Few-Shot Image ClassificationStanford Cars 5-way (1-shot)Accuracy55.85GNN++
Cross-Domain Few-ShotChestX5 shot25.27GNN
Cross-Domain Few-ShotEuroSAT5 shot83.64GNN
Cross-Domain Few-ShotISIC20185 shot43.94GNN

Related Papers

GLAD: Generalizable Tuning for Vision-Language Models2025-07-17A Risk-Aware Adaptive Robust MPC with Learned Uncertainty Quantification2025-07-15Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection2025-07-10An Enhanced Privacy-preserving Federated Few-shot Learning Framework for Respiratory Disease Diagnosis2025-07-10Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat Transport2025-07-08CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization2025-07-08MP-ALOE: An r2SCAN dataset for universal machine learning interatomic potentials2025-07-08ViRefSAM: Visual Reference-Guided Segment Anything Model for Remote Sensing Segmentation2025-07-03