Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence

TL;DR

This study demonstrates that enhanced simple GNN architectures can match or outperform complex Graph Transformers in graph-level tasks, offering a more efficient and effective baseline for future research.

Contribution

The paper introduces GNN+, a framework that significantly improves classic GNNs, showing they can rival or surpass Graph Transformers in performance and efficiency on various datasets.

Findings

Classic GNNs with GNN+ match or outperform GTs in performance.

Enhanced GNNs run several times faster than GTs on many datasets.

Simple GNN architectures can serve as strong baselines for graph-level tasks.

Abstract

Message-passing Graph Neural Networks (GNNs) are often criticized for their limited expressiveness, issues like over-smoothing and over-squashing, and challenges in capturing long-range dependencies. Conversely, Graph Transformers (GTs) are regarded as superior due to their employment of global attention mechanisms, which potentially mitigate these challenges. Literature frequently suggests that GTs outperform GNNs in graph-level tasks, especially for graph classification and regression on small molecular graphs. In this study, we explore the untapped potential of GNNs through an enhanced framework, GNN+, which integrates six widely used techniques: edge feature integration, normalization, dropout, residual connections, feed-forward networks, and positional encoding, to effectively tackle graph-level tasks. We conduct a systematic re-evaluation of three classic GNNs (GCN, GIN, and GatedGCN) enhanced by the GNN+ framework across 14 well-known graph-level datasets. Our results reveal that, contrary to prevailing beliefs, these classic GNNs consistently match or surpass the performance of GTs, securing top-three rankings across all datasets and achieving first place in eight. Furthermore, they demonstrate greater efficiency, running several times faster than GTs on many datasets. This highlights the potential of simple GNN architectures, challenging the notion that complex mechanisms in GTs are essential for superior graph-level performance. Our source code is available at https://github.com/LUOyk1999/GNNPlus.