Bag of Tricks for Node Classification with Graph Neural Networks
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
How Attentive are Graph Attention Networks?
GAT uses static attention where neighbor rankings ignore the query node and thus cannot express some graph problems; GATv2 enables dynamic attention and outperforms GAT on 11 OGB and other benchmarks with equal parameters.
-
Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation
Robust diffusion operators and hidden-state re-propagation improve PPGNN accuracy to match message-passing GNNs on benchmarks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.