{"type":"ScholarlyArticle","title":"Graph Label Denoising via Neighborhood Agreement–Guided Expectation Maximization","authors":[{"name":"Dezhi Liu","slug":"dezhi-liu","given":"Dezhi","family":"Liu","affiliation":""},{"name":"Richong Zhang","slug":"richong-zhang","given":"Richong","family":"Zhang","affiliation":""},{"name":"Junfan Chen","slug":"junfan-chen","given":"Junfan","family":"Chen","affiliation":""},{"name":"Fengbo Tian","slug":"fengbo-tian","given":"Fengbo","family":"Tian","affiliation":""},{"name":"Si Chen","slug":"si-chen","given":"Si","family":"Chen","affiliation":""}],"abstract":"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, we propose NAEM, a latent label estimation framework that models clean labels as latent variables by integrating neighborhood agreement into the Expectation-Maximization (EM) paradigm. To overcome the posterior collapse problem in standard EM under severe noise, we design a structure-aware E-step that leverages neighborhood agreement as a structural prior. This mechanism acts as a dynamic confidence gate based on local consensus to prevent the model from overfitting to noise. Simultaneously, by explicitly modeling the noise transition matrix in the M-step, NAEM decouples noise dynamics from semantic representation learning. Extensive experiments on five benchmark datasets demonstrate that NAEM consistently outperforms SOTA methods under varying noise conditions, validating the effectiveness of our framework.","doi":"10.24963/ijcai.2026/317","url":"https://ijcai.org/proceedings/2026/317","pdf":"https://ijcai.org/proceedings/2026/0317.pdf","markdown":"https://ijcai.org/proceedings/2026/317.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/317","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Data Mining","track":"Main Track","number":317,"pages":{"first":2852,"last":2860},"keywords":["Machine Learning: Weakly supervised learning","Data Mining: Mining graphs"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}