paper-with-me

홈 › Papers

On the Adversarial Robustness of Graph Contrastive Learning Methods

2023-11-29 · Filippo Guerranti, Zinuo Yi, Anna Starovoit, Rafiq Kamel, Simon Geisler, Stephan Günnemann

Contrastive learning (CL) has emerged as a powerful framework for learning representations of images and text in a self-supervised manner while enhancing model robustness against adversarial attacks. More recently, researchers have extended the principles of contrastive learning to graph-structured data, giving birth to the field of graph contrastive learning (GCL). However, whether GCL methods can deliver the same advantages in adversarial robustness as their counterparts in the image and text domains remains an open question. In this paper, we introduce a comprehensive robustness evaluation protocol tailored to assess the robustness of GCL models. We subject these models to adaptive adversarial attacks targeting the graph structure, specifically in the evasion scenario. We evaluate node and graph classification tasks using diverse real-world datasets and attack strategies. With our work, we aim to offer insights into the robustness of GCL methods and hope to open avenues for potential future research directions.

📄 PDF Abstract BibTeX arXiv:2311.17853

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessContrastive LearningGraph ClassificationNode Classification

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
GCA 설명 없음
InfoGraph 설명 없음
AD-GCL 설명 없음
GraphCL 설명 없음
GIN Per the authors, Graph Isomorphism Network (GIN) generalizes the WL test and hence achieves maximum discriminative power among GNNs.
GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…
DGI Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information…

Similar Papers 제목 키워드 기반

Similarity Preserving Adversarial Graph Contrastive Learning

2023-06-24 · Yeonjun In, Kanghoon Yoon, Chanyoung Park

Recent works demonstrate that GNN models are vulnerable to adversarial attacks, which refer to imperceptible perturbation on the graph structure and node features. Among various GNN models, graph contrastive learning (GC…

Adversarial RobustnessContrastive Learning

Towards Robust Graph Contrastive Learning

2021-02-25 · Nikola Jovanović, Zhao Meng, Lukas Faber, Roger Wattenhofer

We study the problem of adversarially robust self-supervised learning on graphs. In the contrastive learning framework, we introduce a new method that increases the adversarial robustness of the learned representations t…

Adversarial RobustnessContrastive LearningSelf-Supervised Learning

Adversarial Graph Contrastive Learning with Information Regularization

2022-02-14 · Shengyu Feng, Baoyu Jing, Yada Zhu, Hanghang Tong

Contrastive learning is an effective unsupervised method in graph representation learning. Recently, the data augmentation based contrastive learning method has been extended from images to graphs. However, most prior wo…

Contrastive LearningData AugmentationGraph Representation LearningNode Classification+1

Learning Robust Representation through Graph Adversarial Contrastive Learning

2022-01-31 · Jiayan Guo, Shangyang Li, Yue Zhao, Yan Zhang

Existing studies show that node representations generated by graph neural networks (GNNs) are vulnerable to adversarial attacks, such as unnoticeable perturbations of adjacent matrix and node features. Thus, it is requis…

Contrastive LearningGraph Representation LearningNode ClassificationRepresentation Learning+1

Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation

2022-01-20 · Sixiao Zhang, Hongxu Chen, Xiangguo Sun, Yicong Li 외

Graph contrastive learning is the state-of-the-art unsupervised graph representation learning framework and has shown comparable performance with supervised approaches. However, evaluating whether the graph contrastive l…

Adversarial AttackContrastive LearningGraph Representation LearningLink Prediction+2