[Video] Introduction about robust structural noise-resistant GNN (WSDM-2022)

Summary: we study a novel problem of developing robust GNNs on noisy graphs with limited labeled nodes. We propose 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.

Papaer link: Enyan Dai, Jin Wei, Hui Liu, and Suhang Wang. “Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels.” Oral in WSDM 2022 [paper, code]