SCR: Training Graph Neural Networks with Consistency Regularization

TL;DR

The paper introduces SCR, a framework that improves graph neural network training by applying consistency regularization strategies, leading to better performance and top leaderboard rankings on large-scale node classification datasets.

Contribution

The paper proposes a novel, general consistency regularization framework for GNNs that effectively balances errors from labeled and unlabeled data, enhancing model performance.

Findings

SCR improves GNN performance on large-scale datasets

SCR achieves top-1 rankings on OGB leaderboards

The framework is compatible with various GNN architectures

Abstract

We present the SCR framework for enhancing the training of graph neural networks (GNNs) with consistency regularization. Regularization is a set of strategies used in Machine Learning to reduce overfitting and improve the generalization ability. However, it is unclear how to best design the generalization strategies in GNNs, as it works in a semi-supervised setting for graph data. The major challenge lies in how to efficiently balance the trade-off between the error from the labeled data and that from the unlabeled data. SCR is a simple yet general framework in which we introduce two strategies of consistency regularization to address the challenge above. One is to minimize the disagreements among the perturbed predictions by different versions of a GNN model. The other is to leverage the Mean Teacher paradigm to estimate a consistency loss between teacher and student models instead of the disagreement of the predictions. We conducted experiments on three large-scale node classification datasets in the Open Graph Benchmark (OGB). Experimental results demonstrate that the proposed SCR framework is a general one that can enhance various GNNs to achieve better performance. Finally, SCR has been the top-1 entry on all three OGB leaderboards as of this submission.