Robust Graph Neural Network

Robust Graph Neural Networks (GNNs) aim to improve the resilience of GNN models against various forms of noise and adversarial attacks, which can significantly degrade their performance on graph-structured data. Current research focuses on developing novel architectures and algorithms, such as those employing weighted Laplacian matrices, contrastive learning, and adaptive message passing schemes, to enhance robustness against structural attacks, noisy edges, and model mismatch during training and testing. This work is crucial for ensuring the reliability and trustworthiness of GNNs in real-world applications, particularly in safety-critical domains where adversarial manipulation could have significant consequences. The development of robust GNNs is driving advancements in both theoretical understanding of GNN vulnerabilities and practical improvements in their performance across diverse applications.

Papers

November 6, 2024

Graph Neural Networks with Coarse- and Fine-Grained Division for Mitigating Label Sparsity and Noise
Shuangjie Li, Baoming Zhang, Jianqing Song, Gaoli Ruan, Chongjun Wang, Junyuan Xie
Graph Neural Network Industrial Disturbing Noise Coarse to Fine Semi Supervised Node Classification Sparse Label Robust Graph Neural Network

September 27, 2024

Enhancing Robustness of Graph Neural Networks through p-Laplacian
Anuj Kumar Sirohi, Subhanu Halder, Kabir Kumar, Sandeep Kumar
Graph Neural Network Adversarial Attack Native Robustness Graph Based Social Network Analysis Robust Graph Neural Network

August 29, 2024

SFR-GNN: Simple and Fast Robust GNNs against Structural Attacks
Xing Ai, Guanyu Zhu, Yulin Zhu, Yu Zheng, Gaolei Li, Jianhua Li, Kai Zhou
Graph Neural Network Gene Level GNN Defense Method Structural Attack Robust Graph Neural Network

August 25, 2024

Generalization of Graph Neural Networks is Robust to Model Mismatch
Zhiyang Wang, Juan Cervino, Alejandro Ribeiro
Graph Neural Network Strong Generalization Generalization Gap Training Graph Model Mismatch Robust Graph Neural Network

July 3, 2024

SF-GNN: Self Filter for Message Lossless Propagation in Deep Graph Neural Network
Yushan Zhu, Wen Zhang, Yajing Xu, Zhen Yao, Mingyang Chen, Huajun Chen
Graph Neural Network Node Representation Robust Graph Neural Network Message Propagation

June 20, 2024

Explainable AI Security: Exploring Robustness of Graph Neural Networks to Adversarial Attacks
Tao Wu, Canyixing Cui, Xingping Xian, Shaojie Qiao, Chao Wang, Lin Yuan, Shui Yu
Graph Neural Network Adversarial Attack Native Robustness Adversarial Example Adversarial Robustness Adversarial Transferability Artificial Intelligence Security Robust Graph Neural Network

November 25, 2023

Robust Graph Neural Networks via Unbiased Aggregation
Zhichao Hou, Ruiqi Feng, Tyler Derr, Xiaorui Liu
Graph Neural Network Adversarial Robustness Robust Graph Neural Network Fairness Aware Aggregation

November 1, 2023

Robust Graph Clustering via Meta Weighting for Noisy Graphs
Hyeonsoo Jo, Fanchen Bu, Kijung Shin
Graph Clustering Noisy Graph Robust Graph Neural Network Clustering Loss Meta Re Weighting

April 9, 2023

Adversarially Robust Neural Architecture Search for Graph Neural Networks
Beini Xie, Heng Chang, Ziwei Zhang, Xin Wang, Daixin Wang, Zhiqiang Zhang, Rex Ying, Wenwu Zhu
Graph Neural Network GNN Architecture DNN Robustness Robust Graph Neural Network Graph Adversarial Attack Robust Neural Architecture Search

October 3, 2022

ASGNN: Graph Neural Networks with Adaptive Structure
Zepeng Zhang, Songtao Lu, Zengfeng Huang, Ziping Zhao
Graph Neural Network Adversarial Attack Adaptive Structure Robust Graph Neural Network

August 3, 2022

Robust Graph Neural Networks using Weighted Graph Laplacian
Bharat Runwal, Vivek, Sandeep Kumar
Graph Neural Network Adversarial Attack Robust Graph Neural Network

January 1, 2022

Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels
Enyan Dai, Wei Jin, Hui Liu, Suhang Wang
Graph Neural Network Sparse Label Dense Graph Noisy Graph Robust Graph Neural Network

December 11, 2021

A Comparative Study on Robust Graph Neural Networks to Structural Noises
Zeyu Zhang, Yulong Pei
Graph Neural Network Comparative Study Node Representation Real World Noise Robust Graph Neural Network