Enhancing the Resilience of Graph Neural Networks to Topological Perturbations in Sparse Graphs
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 31 of its 68 references that are in the map. First posted on arXiv 5 Jun 2024.
Builds on
31 of 68 references.
References · 31
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
- 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
- 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
- 2018Graph Convolutional Networks for Text Classificationcited by 345
- 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
- 2020Bayesian Graph Neural Networks with Adaptive Connection Samplingcited by 81
- 2020Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbationcited by 57
- 2018N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classificationcited by 54
- 2020Random Walks: A Review of Algorithms and Applicationscited by 38
- 2023Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approachcited by 24
19 more
- 2020Topological Insights into Sparse Neural Networkscited by 21
- 2018On a Sparse Shortcut Topology of Artificial Neural Networkscited by 20
- 2023Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regressioncited by 20
- 2022Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervisioncited by 16
- 2023BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learningcited by 16
- 2022RecipeRec: A Heterogeneous Graph Learning Model for Recipe Recommendationcited by 13
- 2022Robust Node Classification on Graphs: Jointly from Bayesian Label Transition and Topology-based Label Propagationcited by 12
- 2022Toward Robust Graph Semi-Supervised Learning against Extreme Data Scarcitycited by 11
- 2023Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularizationcited by 10
- 2023Scalable Multi-agent Covering Option Discovery based on Kronecker Graphscited by 9
- 2021NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labelscited by 8
- 2020Deperturbation of Online Social Networks via Bayesian Label Transitioncited by 6
- 2023Uncertainty-Aware Robust Learning on Noisy Graphscited by 6
- 2023Stability of Graph Convolutional Neural Networks through the lens of small perturbation analysiscited by 5
- 2022Learning Multi-agent Skills for Tabular Reinforcement Learning using Factor Graphscited by 4
- 2023Robust Node Representation Learning via Graph Variational Diffusion Networkscited by 4
- 2013LabelRank: A Stabilized Label Propagation Algorithm for Community Detection in Networkscited by 3
- 2021Multipath Graph Convolutional Neural Networkscited by 1
- 2023Can Directed Graph Neural Networks be Adversarially Robust?cited by 1
Built on by
Citing papers per year: 2024: 2; 2025: 1.
3 papers.