用图拓扑结构优化主动学习，提升小样本下的分类效果
Topology-Aware Active Learning on Graphs
- 基于平衡Forman曲率构建核心数据集，自动选择代表性初始标签
- 在低标签率下优于现有图半监督方法，显著减少人工调参
- 适合资源受限场景的图数据主动学习，如社交网络分析
我们提出一种基于图拓扑结构的主动学习方法，直接应对标签预算稀缺下的探索与利用权衡问题。为引导探索，提出基于平衡Forman曲率（BFC）的核心集构造算法，选取反映图聚类结构的代表性初始标签，并包含数据驱动的停止准则，指示图已充分探索。进一步利用BFC动态触发主动学习流程中从探索到利用的切换，替代人工调参的启发式策略。为提升利用效率，引入局部图重连策略，高效融合标记节点周围的多尺度信息，在保持稀疏性的同时增强标签传播。在基准分类任务上的实验表明，该方法在低标签率下持续优于现有的图半监督基线方法。
原文摘要 · Abstract (English)
We propose a graph-topological approach to active learning that directly targets the core challenge of exploration versus exploitation under scarce label budgets. To guide exploration, we introduce a coreset construction algorithm based on Balanced Forman Curvature (BFC), which selects representative initial labels that reflect the graph's cluster structure. This method includes a data-driven stopping criterion that signals when the graph has been sufficiently explored. We further use BFC to dynamically trigger the shift from exploration to exploitation within active learning routines, replacing hand-tuned heuristics. To improve exploitation, we introduce a localized graph rewiring strategy that efficiently incorporates multiscale information around labeled nodes, enhancing label propagation while preserving sparsity. Experiments on benchmark classification tasks show that our methods consistently outperform existing graph-based semi-supervised baselines at low label rates.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。