Robust Graph

Robust graph research focuses on developing graph neural networks (GNNs) that are resilient to noise, attacks, and inconsistencies in graph data, aiming for reliable performance in real-world applications. Current research emphasizes techniques like subgraph analysis, feature and structure denoising, and the integration of large language models to improve GNN robustness against adversarial perturbations and noisy labels. These advancements are crucial for enhancing the reliability and trustworthiness of GNNs across diverse applications, from social network analysis and drug discovery to anomaly detection and combinatorial optimization. The ultimate goal is to build more dependable and accurate graph-based systems that can handle the inherent imperfections of real-world data.

Papers

October 7, 2024

Defense-as-a-Service: Black-box Shielding against Backdoored Graph Models
Xiao Yang, Kai Zhou, Yuni Lai, Gaolei Li
Large Scale Graph Graph Model Robust Graph Model Based Shielding Graph Backdoor Attack

August 16, 2024

Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?
Zhongjian Zhang, Xiao Wang, Huichi Zhou, Yue Yu, Mengmei Zhang, Cheng Yang, Chuan Shi
Graph Neural Network Native Robustness Adversarial Robustness Adversarial Perturbation Robust Graph

August 1, 2024

You Can't Ignore Either: Unifying Structure and Feature Denoising for Robust Graph Learning
Tianmeng Yang, Jiahao Meng, Min Zhou, Yaming Yang, Yujing Wang, Xiangtai Li, Yunhai Tong
Graph Neural Network Denoising Process Unifying Theory Robust Graph Feature Denoising

June 11, 2024

Rethinking the impact of noisy labels in graph classification: A utility and privacy perspective
De Li, Xianxian Li, Zeming Gan, Qiyu Li, Bin Qu, Jinyan Wang
Global Impact Noisy Label Label Noise Graph Classification Task Utility Robust Graph Graph Privacy

March 14, 2024

Robust Subgraph Learning by Monitoring Early Training Representations
Sepideh Neshatfar, Salimeh Yasaei Sekeh
Adversarial Attack Adversarial Robustness Graph Learning Pre Trained Representation Input Graph Robust Graph

March 6, 2024

Robust Graph Structure Learning under Heterophily
Xuanting Xie, Zhao Kang, Wenyu Chen
Graph Representation Learning Graph Structure Heterophilic Graph Robust Graph

March 4, 2024

Improving out-of-distribution generalization in graphs via hierarchical semantic environments
Yinhua Piao, Sangseon Lee, Yijingxiu Lu, Sun Kim
Strong Generalization Graph Drawing Distribution Generalization Real World Graph Graph Domain Robust Graph Graph Out of Distribution Generalization

February 14, 2024

Subgraph Pooling: Tackling Negative Transfer on Graphs
Zehong Wang, Zheyuan Zhang, Chuxu Zhang, Yanfang Ye
Graph Neural Network Graph Drawing Node Embeddings Graph Pooling Robust Graph Negative Transfer

November 3, 2023

Resist Label Noise with PGM for Graph Neural Networks
Qingqing Ge, Jianxiang Yu, Zeyuan Zhao, Xiang Li
Graph Neural Network Noisy Label Label Noise Probabilistic Graphical Model Robust Graph

October 14, 2023

Efficient Link Prediction via GNN Layers Induced by Negative Sampling
Yuxin Wang, Xiannian Hu, Quan Gan, Xuanjing Huang, Xipeng Qiu, David Wipf
Link Prediction Node Embeddings Negative Sampling Robust Graph GNN Layer

October 10, 2023

Enhanced Graph Neural Networks with Ego-Centric Spectral Subgraph Embeddings Augmentation
Anwar Said, Mudassir Shabbir, Tyler Derr, Waseem Abbas, Xenofon Koutsoukos
Graph Neural Network Graph Classification Subgraph Structure Spectral Graph Neural Network Robust Graph Ego Graph

July 5, 2023

Robust Graph Structure Learning with the Alignment of Features and Adjacency Matrix
Shaogao Lv, Gang Wen, Shiyu Liu, Linsen Wei, Ming Li
Alignment Problem Feature Wise Graph Structure Graph Structure Learning Adjacency Matrix Graph Alignment Robust Graph Noisy Graph

June 14, 2023

Uncertainty-Aware Robust Learning on Noisy Graphs
Shuyi Chen, Kaize Ding, Shixiang Zhu
Robust Optimization Uncertainty Aware Robust Graph Uncertainty Aware Graph Noisy Graph Optimal Embeddings

May 31, 2023

Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization
Kaixuan Chen, Shunyu Liu, Tongtian Zhu, Tongya Zheng, Haofei Zhang, Zunlei Feng, Jingwen Ye, Mingli Song
Graph Neural Network Subgraph Structure Expressivity Transfer Robust Graph Induced Subgraphs

December 1, 2022

Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View
Jingcan Duan, Siwei Wang, Pei Zhang, En Zhu, Jingtao Hu, Hu Jin, Yue Liu, Zhibin Dong
Graph Contrastive Learning Graph Anomaly Detection Anomalous Graph Robust Graph Scale Contrastive Learning Augmented View Maximum Common Subgraph

October 8, 2022

Robust Graph Structure Learning via Multiple Statistical Tests
Yaohua Wang, FangYi Zhang, Ming Lin, Senzhang Wang, Xiuyu Sun, Rong Jin
Graph Structure Graph Structure Learning Pairwise Similarity Robust Graph Multiple Hypothesis Testing

May 20, 2022

LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation
David Ireland, Giovanni Montana
Camera Lens Reinforcement Learning Algorithm Robust Graph Combinatorial Optimisation Problem Non Euclidean Graph Large Scale Combinatorial

April 4, 2022

Multi-Modal Hypergraph Diffusion Network with Dual Prior for Alzheimer Classification
Angelica I. Aviles-Rivero, Christina Runkel, Nicolas Papadakis, Zoe Kourtzi, Carola-Bibiane Schönlieb
Self Supervised Multi Modal Data SAM Prior Robust Graph Hypergraph Diffusion

March 22, 2022

Exploring High-Order Structure for Robust Graph Structure Learning
Guangqian Yang, Yibing Zhan, Jinlong Li, Baosheng Yu, Liu Liu, Fengxiang He
Graph Neural Network Adversarial Attack Adversarial Perturbation Higher Order Robust Graph Order Graph

Robust Graph

Papers

Defense-as-a-Service: Black-box Shielding against Backdoored Graph Models

Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?

You Can't Ignore Either: Unifying Structure and Feature Denoising for Robust Graph Learning

Rethinking the impact of noisy labels in graph classification: A utility and privacy perspective

Robust Subgraph Learning by Monitoring Early Training Representations

Robust Graph Structure Learning under Heterophily

Improving out-of-distribution generalization in graphs via hierarchical semantic environments

Subgraph Pooling: Tackling Negative Transfer on Graphs

Resist Label Noise with PGM for Graph Neural Networks

Efficient Link Prediction via GNN Layers Induced by Negative Sampling

Enhanced Graph Neural Networks with Ego-Centric Spectral Subgraph Embeddings Augmentation

Robust Graph Structure Learning with the Alignment of Features and Adjacency Matrix

Uncertainty-Aware Robust Learning on Noisy Graphs

Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization

Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View

Robust Graph Structure Learning via Multiple Statistical Tests

LeNSE: Learning To Navigate Subgraph Embeddings for Large-Scale Combinatorial Optimisation

Multi-Modal Hypergraph Diffusion Network with Dual Prior for Alzheimer Classification

Exploring High-Order Structure for Robust Graph Structure Learning