Graph Relearn Network (GRN)

The python code of Graph Neural Network (GRN). Recent studies have shown that the predictive performance of graph neural networks (GNNs) is inconsistent and varies across different experimental runs, even with identical parameters. The prediction variability limits GNNs' applicability, and the underlying reasons remain unclear. We have identified a key factor contributing to this issue: the oscillation of some nodes' predicted classes during GNN training. To tackle this problem, we propose a novel framework, the \underline{G}raph \underline{R}elearn \underline{N}etwork (GRN), designed to reduce prediction variance by iteratively refining the predictions of unstable nodes. The GRN framework operates in two phases: pre-predict and re-learn. During the pre-predict phase, a graph-dense encoder is trained to pre-predict the nodes' categories. In the re-learn phase, the model intensively focuses on the unstable nodes to optimize predictions.

Extensive experiments on ten graph datasets demonstrate that the GRN significantly enhances the performance stability of GNNs (with std. reduced up to 75\%), and achieves state-of-the-art performance in prediction accuracy (increasing by up to 11.97\%). By mitigating the disruptions caused by unstable nodes, GRN improves the performance stability of GNNs, and it benefits prediction accuracy in node classification tasks.