Bag of Tricks for Node Classification with Graph Neural Networks

TL;DR

This paper compiles and introduces practical tricks and techniques that significantly enhance the performance of graph neural networks in node classification tasks, often surpassing the gains from complex architectural changes.

Contribution

It summarizes existing best practices and proposes new techniques related to label usage, loss functions, and model design that improve GNN performance.

Findings

Consistent performance improvements across various GNN architectures

Techniques benefit top models on OGB leaderboard and KDDCUP challenge

Ablation studies confirm the impact of each trick

Abstract

Over the past few years, graph neural networks (GNN) and label propagation-based methods have made significant progress in addressing node classification tasks on graphs. However, in addition to their reliance on elaborate architectures and algorithms, there are several key technical details that are frequently overlooked, and yet nonetheless can play a vital role in achieving satisfactory performance. In this paper, we first summarize a series of existing tricks-of-the-trade, and then propose several new ones related to label usage, loss function formulation, and model design that can significantly improve various GNN architectures. We empirically evaluate their impact on final node classification accuracy by conducting ablation studies and demonstrate consistently-improved performance, often to an extent that outweighs the gains from more dramatic changes in the underlying GNN architecture. Notably, many of the top-ranked models on the Open Graph Benchmark (OGB) leaderboard and KDDCUP 2021 Large-Scale Challenge MAG240M-LSC benefit from these techniques we initiated.