Parameter-Free Structural-Diversity Message Passing for Graph Neural Networks
By: Mingyue Kong , Yinglong Zhang , Chengda Xu and more
Potential Business Impact:
Helps computers understand messy data better.
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
Similar Papers
Parameter-Free Structural-Diversity Message Passing for Graph Neural Networks
Machine Learning (CS)
Helps computers understand complex connections better.
Adapting to Heterophilic Graph Data with Structure-Guided Neighbor Discovery
Machine Learning (CS)
Helps computers understand messy data by making connections.
Graph Neural Network Assisted Genetic Algorithm for Structural Dynamic Response and Parameter Optimization
Neural and Evolutionary Computing
Makes buildings stronger and safer faster.