Enhancing the Resilience of Graph Neural Networks to Topological Perturbations in Sparse Graphs

• URL: http://arxiv.org/abs/2406.03097v1
• Date: Wed, 5 Jun 2024 09:40:08 GMT
• Title: Enhancing the Resilience of Graph Neural Networks to Topological Perturbations in Sparse Graphs
• Authors: Shuqi He, Jun Zhuang, Ding Wang, Luyao Peng, Jun Song,
• Abstract summary: We propose a novel label inference framework, TraTopo, which combines topology-driven label propagation, Bayesian label transitions, and link analysis via random walks. TraTopo significantly surpasses its predecessors on sparse graphs by utilizing random walk sampling, specifically targeting isolated nodes for link prediction. Empirical evaluations highlight TraTopo's superiority in node classification, significantly exceeding contemporary GCN models in accuracy.
• Score: 9.437128738619563
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph neural networks (GNNs) have been extensively employed in node classification. Nevertheless, recent studies indicate that GNNs are vulnerable to topological perturbations, such as adversarial attacks and edge disruptions. Considerable efforts have been devoted to mitigating these challenges. For example, pioneering Bayesian methodologies, including GraphSS and LlnDT, incorporate Bayesian label transitions and topology-based label sampling to strengthen the robustness of GNNs. However, GraphSS is hindered by slow convergence, while LlnDT faces challenges in sparse graphs. To overcome these limitations, we propose a novel label inference framework, TraTopo, which combines topology-driven label propagation, Bayesian label transitions, and link analysis via random walks. TraTopo significantly surpasses its predecessors on sparse graphs by utilizing random walk sampling, specifically targeting isolated nodes for link prediction, thus enhancing its effectiveness in topological sampling contexts. Additionally, TraTopo employs a shortest-path strategy to refine link prediction, thereby reducing predictive overhead and improving label inference accuracy. Empirical evaluations highlight TraTopo's superiority in node classification, significantly exceeding contemporary GCN models in accuracy.

Related papers

• HGAttack: Transferable Heterogeneous Graph Adversarial Attack [63.35560741500611]
  Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce. This paper introduces HGAttack, the first dedicated gray box evasion attack method for heterogeneous graphs.
  arXiv  Detail & Related papers  (2024-01-18T12:47:13Z)
• A GAN Approach for Node Embedding in Heterogeneous Graphs Using Subgraph Sampling [35.94125831564648]
  Our research addresses class imbalance issues in heterogeneous graphs using graph neural networks (GNNs) We propose a novel method combining the strengths of Generative Adversarial Networks (GANs) with GNNs, creating synthetic nodes and edges that effectively balance the dataset.
  arXiv  Detail & Related papers  (2023-12-11T16:52:20Z)
• BOURNE: Bootstrapped Self-supervised Learning Framework for Unified Graph Anomaly Detection [50.26074811655596]
  We propose a novel unified graph anomaly detection framework based on bootstrapped self-supervised learning (named BOURNE) By swapping the context embeddings between nodes and edges, we enable the mutual detection of node and edge anomalies. BOURNE can eliminate the need for negative sampling, thereby enhancing its efficiency in handling large graphs.
  arXiv  Detail & Related papers  (2023-07-28T00:44:57Z)
• Pseudo Contrastive Learning for Graph-based Semi-supervised Learning [67.37572762925836]
  Pseudo Labeling is a technique used to improve the performance of Graph Neural Networks (GNNs) We propose a general framework for GNNs, termed Pseudo Contrastive Learning (PCL)
  arXiv  Detail & Related papers  (2023-02-19T10:34:08Z)
• Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation [60.50994154879244]
  Recent studies show that Graph Neural Networks are vulnerable and easily fooled by small perturbations. In this work, we focus on the emerging but critical attack, namely, Graph Injection Attack. We propose a general defense framework CHAGNN against GIA through cooperative homophilous augmentation of graph data and model.
  arXiv  Detail & Related papers  (2022-11-15T11:44:31Z)
• Robust Node Classification on Graphs: Jointly from Bayesian Label Transition and Topology-based Label Propagation [5.037076816350975]
  In recent years, evidence emerges that the performance of GNN-based node classification may deteriorate substantially by topological perturbations. We propose a new label inference model, namely LInDT, which integrates both Bayesian label transition and topology-based label propagation. Experiments on five graph datasets demonstrate the superiority of LInDT for GNN-based node classification under three scenarios of topological perturbations.
  arXiv  Detail & Related papers  (2022-08-21T01:56:25Z)
• Cyclic Label Propagation for Graph Semi-supervised Learning [52.102251202186025]
  We introduce a novel framework for graph semi-supervised learning called CycProp. CycProp integrates GNNs into the process of label propagation in a cyclic and mutually reinforcing manner. In particular, our proposed CycProp updates the node embeddings learned by GNN module with the augmented information by label propagation.
  arXiv  Detail & Related papers  (2020-11-24T02:55:40Z)
• Learning to Drop: Robust Graph Neural Network via Topological Denoising [50.81722989898142]
  We propose PTDNet, a parameterized topological denoising network, to improve the robustness and generalization performance of Graph Neural Networks (GNNs) PTDNet prunes task-irrelevant edges by penalizing the number of edges in the sparsified graph with parameterized networks. We show that PTDNet can improve the performance of GNNs significantly and the performance gain becomes larger for more noisy datasets.
  arXiv  Detail & Related papers  (2020-11-13T18:53:21Z)
• Deperturbation of Online Social Networks via Bayesian Label Transition [5.037076816350975]
  Online social networks (OSNs) classify users into different categories based on their online activities and interests. A small number of users, so-called perturbators, may perform random activities on an OSN, which significantly deteriorate the performance of a GCN-based node classification task. We develop a GCN defense model, namely GraphLT, which uses the concept of label transition.
  arXiv  Detail & Related papers  (2020-10-27T08:15:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.