Bag of Tricks for Node Classification with Graph Neural Networks
This work addresses the need for better performance in node classification tasks for researchers and practitioners, but it is incremental as it builds on existing methods with optimizations.
The paper tackles the problem of improving node classification with graph neural networks by identifying and proposing technical tricks, such as label usage and loss function adjustments, that consistently enhance performance, often surpassing gains from architectural changes, as evidenced by top rankings on benchmarks like OGB and MAG240M-LSC.
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.