分形图对比学习
Fractal Graph Contrastive Learning
AI总结：
本文提出分形图对比学习框架，通过引入分形维度感知的对比损失和改进的全局增强策略，提升图对比学习的结构一致性与性能。
摘要：
图对比学习（GCL）依赖于语义一致的图增强，但常见的局部扰动对全局结构一致性控制有限，因此提出分形图对比学习（FractalGCL）框架，构建基于重整化的方法，并引入分形维度感知的对比损失，通过有限尺度盒计数差异重新加权负对排斥。计算这些差异带来显著开销，因此推导并证明了高斯替代方法，避免重复计算重整化图的盒计数，减少约61%的运行时间。实验表明，FractalGCL在MalNet-Tiny上作为有效的冻结预训练工具，标准TUDataset基准测试中表现优异，并在真实城市交通任务中以平均准确率提升4.51个百分点优于次优方法。代码可在https://anonymous.4open.science/r/FractalGCL-0511/获取。
英文摘要：
Graph Contrastive Learning (GCL) relies on semantically consistent graph augmentations, but common local perturbations provide limited control over global structural consistency, motivating a more principled global augmentation strategy. We therefore propose Fractal Graph Contrastive Learning (FractalGCL), a theory-motivated framework that constructs a renormalisation-based augmented graph and introduces a fractal-dimension-aware contrastive loss that penalises unreliable positive views and reweights negative-pair repulsion by finite-scale box-counting discrepancies. However, computing these discrepancies introduces substantial overhead, so we derive and justify a Gaussian surrogate that avoids repeated box-counting on renormalised graphs, yielding about a $61\%$ runtime reduction. Experiments show that FractalGCL serves as an effective frozen-pretraining tool on MalNet-Tiny, achieves strong performance on the standard TUDataset benchmarks, and outperforms the next-best method on real-world urban traffic tasks by $4.51$ percentage points in average accuracy. Code is available at https://anonymous.4open.science/r/FractalGCL-0511/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
