{"type":"ScholarlyArticle","title":"Adversarial Masked Graph Modeling for Robust Graph Autoencoders","authors":[{"name":"Qiqi Zhang","slug":"qiqi-zhang","given":"Qiqi","family":"Zhang","affiliation":""},{"name":"Chuanjin Liu","slug":"chuanjin-liu","given":"Chuanjin","family":"Liu","affiliation":""},{"name":"Gen Liu","slug":"gen-liu","given":"Gen","family":"Liu","affiliation":""},{"name":"Chao Li","slug":"chao-li","given":"Chao","family":"Li","affiliation":""},{"name":"Zhongying Zhao","slug":"zhongying-zhao","given":"Zhongying","family":"Zhao","affiliation":""}],"abstract":"Graph Masked AutoEncoders (GMAEs) have achieved notable success in diverse downstream tasks. However, their superior performance usually relies on reliable and unperturbed input graphs. In real-world scenarios, graphs are vulnerable to adversarial attacks (e.g., perturbations on node features or topology). As a result, existing GMAEs tend to overfit these perturbed inputs, leading to poor robustness. Motivated by this, we propose an adversarial masked graph modeling for robust graph autoencoders, named ArmorGAE. Specifically, we first design a dual-consistency graph augmentation method that enriches the graph topology to mitigate structural vulnerabilities. Theoretically, we establish a connection between ArmorGAE and contrastive learning. It demonstrates that our augmentation strategy in GMAEs is equivalent to effectively expanding the set of high-quality positive samples in contrastive learning, providing richer and more reliable supervisory signals. We then present an adversarial masked autoencoder to mitigate model overfitting to the perturbed graph. The generator and discriminator are jointly trained under an adversarial paradigm, where the former aims to recover the underlying true data distribution, while the latter distinguishes reconstructed and real edges. Experimental results on five datasets demonstrate that ArmorGAE outperforms state-of-the-art methods in terms of classification accuracy on clean graphs and adversarial robustness under 16 distinct adversarial scenarios. The codes are publicly available at https://github.com/ZZY-GraphMiningLab/ArmorGAE.","doi":"10.24963/ijcai.2026/592","url":"https://ijcai.org/proceedings/2026/592","pdf":"https://ijcai.org/proceedings/2026/0592.pdf","markdown":"https://ijcai.org/proceedings/2026/592.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/592","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":"Machine Learning","track":"Main Track","number":592,"pages":{"first":5315,"last":5323},"keywords":["Machine Learning: Robustness","Machine Learning: Adversarial machine learning","Machine Learning: Self-supervised Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}