提出节点级自适应谱融合方法，提升图对比学习效果
ASPECT: Node-Level Adaptive Spectral Fusion for Graph Contrastive Learning
- 在节点层面动态融合高低频图信号，避免全局融合偏差
- 在同质与异质图数据集上优于现有谱对比与图对比基线
- 适合需要高精度图表示的复杂网络分析任务
谱图对比学习通常构建低频和高频视图以捕捉互补图信号，但这些视图常通过图级或节点无关的融合规则结合。我们发现，在具有分离节点谱偏好混合图中，图级融合会引入不可消除的损失。为此，我们提出ASPECT，一种在节点层面自适应融合低频与高频视图的谱图对比学习方法。ASPECT学习节点级谱策略，并利用通道级对比证据进行正则化，使不同节点可采用不同的谱混合方式。我们进一步引入ASPECT-S，一个可选的稳定性感知扩展，通过生成图结构与特征扰动，获得经验式的通道级敏感度估计，并结合基于Rayleigh的谱搜索偏差，生成更具信息量的扰动。在同质与异质基准测试上，ASPECT在表示质量上超越多个竞争性谱与图对比基线；而ASPECT-S在联合图结构与特征扰动下表现更优。
原文摘要 · Abstract (English)
Spectral graph contrastive learning often constructs low- and high-frequency views to capture complementary graph signals, but these views are commonly combined by graph-level or node-agnostic fusion rules. We show that graph-level fusion can incur irreducible regret on mixed graphs with separated node-wise spectral preferences. Motivated by this result, we propose ASPECT, a spectral graph contrastive learning method that adaptively fuses low- and high-frequency views at the node level. ASPECT learns a node-wise spectral policy and regularizes it using channel-wise contrastive evidence, enabling different nodes to use different spectral mixtures. We further introduce ASPECT-S, an optional stability-aware extension that uses generated graph-structure and feature perturbations to obtain empirical channel-wise sensitivity estimates, together with a Rayleigh-based spectral search bias for producing informative perturbations. Experiments on homophilic and heterophilic benchmarks show that ASPECT improves representation quality over competitive spectral and graph contrastive baselines, while ASPECT-S further improves performance under joint graph-structure and feature perturbations.
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。