SF-GNN: Self Filter for Message Lossless Propagation in Deep Graph Neural Network

TL;DR

SF-GNN introduces a self-filter mechanism that evaluates and selectively propagates node representations, effectively mitigating performance degradation in deep GNNs across various graph types.

Contribution

The paper proposes SF-GNN, a novel self-filter module that improves deep GNN performance by filtering low-quality node representations during message passing.

Findings

Outperforms state-of-the-art methods in node classification.

Enhances deep GNN stability across different graph types.

Applicable to various GNN architectures.

Abstract

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.