Prioritized Propagation in Graph Neural Networks
This work addresses a specific bottleneck in GNNs for graph learning tasks, offering an incremental improvement by integrating priority considerations into existing models.
The paper tackles the problem of ignoring node priority in graph neural networks by proposing PPro, a framework that learns prioritized node-wise message propagation, leading to superior performance compared to 11 state-of-the-art competitors on 8 benchmark datasets.
Graph neural networks (GNNs) have recently received significant attention. Learning node-wise message propagation in GNNs aims to set personalized propagation steps for different nodes in the graph. Despite the success, existing methods ignore node priority that can be reflected by node influence and heterophily. In this paper, we propose a versatile framework PPro, which can be integrated with most existing GNN models and aim to learn prioritized node-wise message propagation in GNNs. Specifically, the framework consists of three components: a backbone GNN model, a propagation controller to determine the optimal propagation steps for nodes, and a weight controller to compute the priority scores for nodes. We design a mutually enhanced mechanism to compute node priority, optimal propagation step and label prediction. We also propose an alternative optimization strategy to learn the parameters in the backbone GNN model and two parametric controllers. We conduct extensive experiments to compare our framework with other 11 state-of-the-art competitors on 8 benchmark datasets. Experimental results show that our framework can lead to superior performance in terms of propagation strategies and node representations.