Conference
Open access
Sep 2026
Graph Label Denoising via Neighborhood Agreement–Guided Expectation Maximization
Graph Neural Networks are susceptible to label noise, in which message-passing mechanisms serve as conduits for propagating erroneous supervision. Current mitigation techniques typically recover clean labels via heuristics that lack theoretical grounding, which often leads to ineffective denoising. To tackle the issue,...
De-Zhi Liu, Richong Zhang, J. Chen et al.
· Proceedings of the Thirty-Fi... · 0 citations