Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels
This addresses a practical issue for applications using GNNs on real-world data, but it is incremental as it builds on existing GNN methods to handle specific noise and label limitations.
The paper tackles the problem of Graph Neural Networks (GNNs) performing poorly on noisy graphs with sparse labels by proposing a framework that uses noisy edges as supervision to learn a denoised graph, which improves message passing and regularization, achieving robustness in experiments on real-world datasets.
Graph Neural Networks (GNNs) have shown their great ability in modeling graph structured data. However, real-world graphs usually contain structure noises and have limited labeled nodes. The performance of GNNs would drop significantly when trained on such graphs, which hinders the adoption of GNNs on many applications. Thus, it is important to develop noise-resistant GNNs with limited labeled nodes. However, the work on this is rather limited. Therefore, we study a novel problem of developing robust GNNs on noisy graphs with limited labeled nodes. Our analysis shows that both the noisy edges and limited labeled nodes could harm the message-passing mechanism of GNNs. To mitigate these issues, we propose a novel framework which adopts the noisy edges as supervision to learn a denoised and dense graph, which can down-weight or eliminate noisy edges and facilitate message passing of GNNs to alleviate the issue of limited labeled nodes. The generated edges are further used to regularize the predictions of unlabeled nodes with label smoothness to better train GNNs. Experimental results on real-world datasets demonstrate the robustness of the proposed framework on noisy graphs with limited labeled nodes.