LHGEL: Large Heterogeneous Graph Ensemble Learning using Batch View Aggregation

Abstract--Learning from large heterogeneous graphs presents significant challenges due to the scale of networks, heterogeneity in node and edge types, variations in nodal features, and complex local neighborhood structures. Y et, the crux lies in combining these learners to meet global optimization objective while maintaining computational efficiency on large-scale graphs. In response, we propose LHGEL, an ensemble framework that addresses these challenges through batch sampling with three key components, namely batch view aggregation, residual attention, and diversity regularization. Specifically, batch view aggregation samples subgraphs and forms multiple graph views, while residual attention adaptively weights the contributions of these views to guide node embeddings toward informative subgraphs, thereby improving the accuracy of base learners. Diversity regularization encourages representational disparity across embedding matrices derived from different views, promoting model diversity and ensemble robustness. Our theoretical study demonstrates that residual attention mitigates gradient vanishing issues commonly faced in ensemble learning. Empirical results on five real heterogeneous networks validate that our LHGEL approach consistently outperforms its state-of-the-art competitors by substantial margin. Ensemble learning strives to combine predictions from multiple base learners to improve model accuracy and robustness.