无需参数的图神经网络，通过结构多样性提升泛化能力。
Parameter-Free Structural-Diversity Message Passing for Graph Neural Networks
- 基于结构多样性设计无参消息传递机制，融合结构与特征双视角。
- 在8个数据集上优于主流GNN，尤其在低监督和跨域场景表现突出。
- 适合需要轻量、自适应图模型的研究者或工业落地场景。
图神经网络（GNN）在节点分类等结构化数据建模任务中表现出色，但主流方法依赖大量可训练参数和固定聚合规则，难以适应结构异质性强、特征分布复杂的图数据，常导致节点表示过平滑和语义退化。为此，本文提出一种基于结构多样性的无参图神经网络框架SDGNN（Structural-Diversity GNN）。该框架受结构多样性理论启发，设计统一的结构多样性消息传递机制，同时捕捉邻域结构异质性与特征语义稳定性，且不引入额外可训练参数。与传统参数化方法不同，SDGNN不依赖复杂训练，而是通过结构驱动与特征驱动的互补建模，显著提升在不同数据集与场景下的适应性。实验结果表明，在八个公开基准数据集及跨学科PubMed引用网络上，SDGNN在低监督、类别不平衡和跨域迁移等挑战性条件下持续优于主流GNN。本工作为无参图神经网络的设计提供了新理论视角与通用方法，并进一步验证了结构多样性作为图表示学习核心信号的重要性。为促进复现与研究，SDGNN完整实现已开源：https://github.com/mingyue15694/SGDNN/tree/main
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have shown remarkable performance in structured data modeling tasks such as node classification. However, mainstream approaches generally rely on a large number of trainable parameters and fixed aggregation rules, making it difficult to adapt to graph data with strong structural heterogeneity and complex feature distributions. This often leads to over-smoothing of node representations and semantic degradation. To address these issues, this paper proposes a parameter-free graph neural network framework based on structural diversity, namely SDGNN (Structural-Diversity Graph Neural Network). The framework is inspired by structural diversity theory and designs a unified structural-diversity message passing mechanism that simultaneously captures the heterogeneity of neighborhood structures and the stability of feature semantics, without introducing additional trainable parameters. Unlike traditional parameterized methods, SDGNN does not rely on complex model training, but instead leverages complementary modeling from both structure-driven and feature-driven perspectives, thereby effectively improving adaptability across datasets and scenarios. Experimental results show that on eight public benchmark datasets and an interdisciplinary PubMed citation network, SDGNN consistently outperforms mainstream GNNs under challenging conditions such as low supervision, class imbalance, and cross-domain transfer. This work provides a new theoretical perspective and general approach for the design of parameter-free graph neural networks, and further validates the importance of structural diversity as a core signal in graph representation learning. To facilitate reproducibility and further research, the full implementation of SDGNN has been released at: https://github.com/mingyue15694/SGDNN/tree/main
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。