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.

翻译：图神经网络（GNN）已被广泛用于节点分类任务。然而，近期研究表明，GNN易受拓扑扰动影响，例如对抗攻击和边扰动。已有大量工作致力于缓解这些挑战。例如，包括GraphSS和LlnDT在内的开创性贝叶斯方法，通过引入贝叶斯标签转移和基于拓扑的标签采样来增强GNN的鲁棒性。但GraphSS存在收敛缓慢的问题，而LlnDT在稀疏图中面临挑战。为克服这些局限，我们提出一种新颖的标签推断框架TraTopo，该框架融合了拓扑驱动标签传播、贝叶斯标签转移以及基于随机游走的链接分析。TraTopo通过采用随机游走采样，特别是针对孤立节点进行链接预测，从而在拓扑采样场景中显著提升其在稀疏图上的效能。此外，TraTopo利用最短路径策略优化链接预测，从而降低预测开销并提高标签推断精度。实验评估凸显了TraTopo在节点分类中的优越性，其在准确性上显著超越当前主流的GCN模型。