用中心性特征增强图神经网络，提升模型区分能力
Enhancing GNNs with Architecture-Agnostic Graph Transformations: A Systematic Analysis
- 通过节点中心性等方法改造图结构，提升模型表达能力
- 添加中心性特征可稳定提升图区分性能，但部分方法引入数值误差
- 对高阶同构图仍有限，适合基础图分类任务研究者
近年来涌现了多种图神经网络架构，各有优劣。为提升性能，常采用重连、提升和节点中心性标注等预处理方法。然而缺乏统一最佳实践，架构与预处理对性能的影响尚不明确。本研究系统分析多种图变换作为预处理在主流GNN架构上的表现，以区分非同构图的能力（即表达性）为评价标准。结果表明，将节点特征与中心性度量结合的变换能持续提升表达性；但如图编码等方法虽增强表达性，却可能因常用Python工具包引入数值不准确。此外，这些预处理在处理3-WL与4-WL不可区分的复杂图任务时效果有限。
原文摘要 · Abstract (English)
In recent years, a wide variety of graph neural network (GNN) architectures have emerged, each with its own strengths, weaknesses, and complexities. Various techniques, including rewiring, lifting, and node annotation with centrality values, have been employed as pre-processing steps to enhance GNN performance. However, there are no universally accepted best practices, and the impact of architecture and pre-processing on performance often remains opaque. This study systematically explores the impact of various graph transformations as pre-processing steps on the performance of common GNN architectures across standard datasets. The models are evaluated based on their ability to distinguish non-isomorphic graphs, referred to as expressivity. Our findings reveal that certain transformations, particularly those augmenting node features with centrality measures, consistently improve expressivity. However, these gains come with trade-offs, as methods like graph encoding, while enhancing expressivity, introduce numerical inaccuracies widely-used python packages. Additionally, we observe that these pre-processing techniques are limited when addressing complex tasks involving 3-WL and 4-WL indistinguishable graphs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。