Graph Prototypical Networks for Few-shot Learning on Attributed Networks

TL;DR

This paper introduces Graph Prototypical Networks, a meta-learning framework designed to improve few-shot node classification on attributed networks by extracting meta-knowledge and assessing instance informativeness.

Contribution

It proposes a novel graph meta-learning approach that constructs semi-supervised tasks to enhance few-shot learning on attributed networks, addressing key challenges in the field.

Findings

GPN outperforms existing methods in few-shot node classification.

The framework effectively extracts meta-knowledge for generalization.

Experimental results demonstrate superior performance of GPN.

Abstract

Attributed networks nowadays are ubiquitous in a myriad of high-impact applications, such as social network analysis, financial fraud detection, and drug discovery. As a central analytical task on attributed networks, node classification has received much attention in the research community. In real-world attributed networks, a large portion of node classes only contain limited labeled instances, rendering a long-tail node class distribution. Existing node classification algorithms are unequipped to handle the \textit{few-shot} node classes. As a remedy, few-shot learning has attracted a surge of attention in the research community. Yet, few-shot node classification remains a challenging problem as we need to address the following questions: (i) How to extract meta-knowledge from an attributed network for few-shot node classification? (ii) How to identify the informativeness of each labeled instance for building a robust and effective model? To answer these questions, in this paper, we propose a graph meta-learning framework -- Graph Prototypical Networks (GPN). By constructing a pool of semi-supervised node classification tasks to mimic the real test environment, GPN is able to perform \textit{meta-learning} on an attributed network and derive a highly generalizable model for handling the target classification task. Extensive experiments demonstrate the superior capability of GPN in few-shot node classification.