Edge-labeling Graph Neural Network for Few-shot Learning

Abstract

In this paper, we propose a novel edge-labeling graph neural network (EGNN), which adapts a deep neural network on the edge-labeling graph, for few-shot learning. The previous graph neural network (GNN) approaches in few-shot learning have been based on the node-labeling framework, which implicitly models the intra-cluster similarity and the inter-cluster dissimilarity. In contrast, the proposed EGNN learns to predict the edge-labels rather than the node-labels on the graph that enables the evolution of an explicit clustering by iteratively updating the edge-labels with direct exploitation of both intra-cluster similarity and the inter-cluster dissimilarity. It is also well suited for performing on various numbers of classes without retraining, and can be easily extended to perform a transductive inference. The parameters of the EGNN are learned by episodic training with an edge-labeling loss to obtain a well-generalizable model for unseen low-data problem. On both of the supervised and semi-supervised few-shot image classification tasks with two benchmark datasets, the proposed EGNN significantly improves the performances over the existing GNNs.

accepted to CVPR 2019

References in corpus (13)

• Prototypical Networks for Few-shot Learning
• Inductive Representation Learning on Large Graphs
• Spectral Networks and Locally Connected Networks on Graphs
• Deep Convolutional Networks on Graph-Structured Data
• Matching Networks for One Shot Learning
• A Simple Neural Attentive Meta-Learner
• Few-Shot Learning with Graph Neural Networks
• How Powerful are Graph Neural Networks?
• Neural Relational Inference for Interacting Systems
• Neural Optimizer Search with Reinforcement Learning
• Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
• Evolved Policy Gradients
• Low-Shot Learning from Imaginary Data

Cited by in corpus (13)

• BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification
• Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector
• Adversarial Feature Hallucination Networks for Few-Shot Learning
• Relational Generalized Few-Shot Learning
• A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings
• Few-Shot Learning as Domain Adaptation: Algorithm and Analysis
• Learning from the Past: Continual Meta-Learning via Bayesian Graph Modeling
• Adaptive-Step Graph Meta-Learner for Few-Shot Graph Classification
• Hierarchical Representation based Query-Specific Prototypical Network for Few-Shot Image Classification
• Few Shot Activity Recognition Using Variational Inference
• Few-shot Continual Learning: a Brain-inspired Approach
• Named Entity Normalization Model Using Edge Weight Updating Neural Network: Assimilation Between Knowledge-Driven Graph and Data-Driven Graph
• Mutual-Information Based Few-Shot Classification