Curriculum Learning for Graph Neural Networks: A Multiview Competence-based Approach

TL;DR

This paper introduces a multiview competence-based curriculum learning approach for graph neural networks, leveraging graph complexity formalisms and model competence to improve training efficiency and effectiveness.

Contribution

It proposes a novel curriculum learning method that incorporates multiple difficulty criteria and model competence, advancing graph neural network training strategies.

Findings

Improved performance on link prediction tasks

Enhanced node classification accuracy

Effective curriculum scheduling scheme

Abstract

A curriculum is a planned sequence of learning materials and an effective one can make learning efficient and effective for both humans and machines. Recent studies developed effective data-driven curriculum learning approaches for training graph neural networks in language applications. However, existing curriculum learning approaches often employ a single criterion of difficulty in their training paradigms. In this paper, we propose a new perspective on curriculum learning by introducing a novel approach that builds on graph complexity formalisms (as difficulty criteria) and model competence during training. The model consists of a scheduling scheme which derives effective curricula by accounting for different views of sample difficulty and model competence during training. The proposed solution advances existing research in curriculum learning for graph neural networks with the ability to incorporate a fine-grained spectrum of graph difficulty criteria in their training paradigms. Experimental results on real-world link prediction and node classification tasks illustrate the effectiveness of the proposed approach.