# GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks

arXiv: https://arxiv.org/abs/2606.01560 · HTML: https://mlsanity.com/paper/2606.01560/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 55 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [Graph Structure Learning for Robust Graph Neural Networks](https://mlsanity.com/paper/2005.10203/) (2020)
- [Adversarial Attack on Graph Structured Data](https://mlsanity.com/paper/1806.02371/) (2018)
- [Adversarial Attacks on Graph Neural Networks via Meta Learning](https://mlsanity.com/paper/1902.08412/) (2019)
- [Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective](https://mlsanity.com/paper/1906.04214/) (2019)
- [Node Similarity Preserving Graph Convolutional Networks](https://mlsanity.com/paper/2011.09643/) (2020)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure](https://mlsanity.com/paper/1902.08226/) (2019)
- [Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure](https://mlsanity.com/paper/2209.14107/) (2022)
- [Factorizable Graph Convolutional Networks](https://mlsanity.com/paper/2010.05421/) (2020)
- [TDGIA:Effective Injection Attacks on Graph Neural Networks](https://mlsanity.com/paper/2106.06663/) (2021)
- [Robust Optimization as Data Augmentation for Large-scale Graphs](https://mlsanity.com/paper/2010.09891/) (2020)
- [Deep Open Intent Classification with Adaptive Decision Boundary](https://mlsanity.com/paper/2012.10209/) (2020)
- [Independence Promoted Graph Disentangled Networks](https://mlsanity.com/paper/1911.11430/) (2019)
- [Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain](https://mlsanity.com/paper/2103.04302/) (2021)
- [Spectral Adversarial Training for Robust Graph Neural Network](https://mlsanity.com/paper/2211.10896/) (2022)
- [Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcity](https://mlsanity.com/paper/2208.12422/) (2022)
- [Towards Understanding Adversarial Examples Systematically: Exploring Data Size, Task and Model Factors](https://mlsanity.com/paper/1902.11019/) (2019)
- [Robust Graph Neural Networks via Unbiased Aggregation](https://mlsanity.com/paper/2311.14934/) (2023)
- [Understanding Deep Learning via Decision Boundary](https://mlsanity.com/paper/2206.01515/) (2022)
- [FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification](https://mlsanity.com/paper/2210.13815/) (2022)
- [Adversarial Graph Disentanglement](https://mlsanity.com/paper/2103.07295/) (2021)
- [Node Injection for Class-specific Network Poisoning](https://mlsanity.com/paper/2301.12277/) (2023)
- [Towards Adversarially Robust Recommendation from Adaptive Fraudster Detection](https://mlsanity.com/paper/2211.11534/) (2022)
- [Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learning](https://mlsanity.com/paper/2305.02901/) (2023)

## Abstract (arXiv)

Graph Neural Networks (GNNs) are vulnerable to adversarial attacks, which inherently invert connectivity patterns by introducing disassortative edges in assortative graphs and assortative edges in disassortative graphs. This structural inversion creates structure-feature mismatches that disrupt neighborhood aggregation across different graph types. However, we find that existing defenses are limited, as they either treat neighborhoods as monolithic under fixed assortativity assumptions or rely on standard softmax classifiers that fail to account for perturbation-induced representation shifts. To further exploit this observation, we adopt a robustness perspective that jointly disentangles node representations and decision spaces, isolating perturbation effects while enforcing well-separated decision regions. Based on this principle, we propose Graph Joint Disentanglement Network (GJDNet), a unified framework for robust node classification across diverse graph assortativity regimes. GJDNet enhances robustness at both representation and decision levels: it employs feature-driven soft structural disentanglement with skewness-aware neighbor filtering to suppress perturbation-induced structure-feature mismatches, and introduces a Spherical Decision Boundary (SDB) to promote intra-class compactness and inter-class separation in the embedding space, thereby stabilizing decision boundaries under perturbations. Theoretical analysis provides insights into the effectiveness of the proposed disentangled representation and decision mechanisms, while extensive experiments demonstrate that GJDNet consistently achieves strong robustness across graphs with different connectivity regimes.