SF-GNN: Self Filter for Message Lossless Propagation in Deep Graph Neural Network
This addresses a critical issue in deep GNNs for researchers and practitioners in graph learning, offering a novel perspective and method to improve performance, though it is incremental as it builds on existing GNN frameworks.
The paper tackles the problem of performance degradation in deep Graph Neural Networks (GNNs) by attributing it to interference from low-quality node representations during message propagation, and introduces SF-GNN, a method that uses a self-filter module to selectively integrate node representations into propagation, achieving state-of-the-art results on node classification and link prediction tasks.
Graph Neural Network (GNN), with the main idea of encoding graph structure information of graphs by propagation and aggregation, has developed rapidly. It achieved excellent performance in representation learning of multiple types of graphs such as homogeneous graphs, heterogeneous graphs, and more complex graphs like knowledge graphs. However, merely stacking GNN layers may not improve the model's performance and can even be detrimental. For the phenomenon of performance degradation in deep GNNs, we propose a new perspective. Unlike the popular explanations of over-smoothing or over-squashing, we think the issue arises from the interference of low-quality node representations during message propagation. We introduce a simple and general method, SF-GNN, to address this problem. In SF-GNN, we define two representations for each node, one is the node representation that represents the feature of the node itself, and the other is the message representation specifically for propagating messages to neighbor nodes. A self-filter module evaluates the quality of the node representation and decides whether to integrate it into the message propagation based on this quality assessment. Experiments on node classification tasks for both homogeneous and heterogeneous graphs, as well as link prediction tasks on knowledge graphs, demonstrate that our method can be applied to various GNN models and outperforms state-of-the-art baseline methods in addressing deep GNN degradation.