Ensemble Learning for Graph Neural Networks

2023/10/22 by Zhen Hao Wong, Ling Yue, Wong, Zhen Hao +3 · 1 citation
Computer Science · #Advanced Graph Neural Networks #FOS: Computer and information sciences #Graph Theory and Algorithms #Machine Learning (cs.LG) #Online Learning and Analytics

paper · pdf · doi:10.48550/arxiv.2310.14166

openalex publication_date 2023/10/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Graph Neural Networks (GNNs) have shown success in various fields for learning from graph-structured data. This paper investigates the application of ensemble learning techniques to improve the performance and robustness of Graph Neural Networks (GNNs). By training multiple GNN models with diverse initializations or architectures, we create an ensemble model named ELGNN that captures various aspects of the data and uses the Tree-Structured Parzen Estimator algorithm to determine the ensemble weights. Combining the predictions of these models enhances overall accuracy, reduces bias and variance, and mitigates the impact of noisy data. Our findings demonstrate the efficacy of ensemble learning in enhancing GNN capabilities for analyzing complex graph-structured data. The code is public at https://github.com/wongzhenhao/ELGNN.

Cited by

• Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?

Related

• E2GNN: Efficient Graph Neural Network Ensembles for Semi-Supervised Classification
• GNN-Ensemble: Towards Random Decision Graph Neural Networks
• HGEN: Heterogeneous Graph Ensemble Networks
• Can Large Language Models Act as Ensembler for Multi-GNNs?
• Graph Neural Networks Powered by Encoder Embedding for Improved Node Learning