首次揭示图任务中异质性对模型性能的影响机制。
Exploring Heterophily in Graph-level Tasks
- 提出图级标签分类法，聚焦局部结构中的模式检测任务。
- 理论证明模式识别需混合频率动态，而非全局频率主导。
- 实验证明频率自适应模型在分子属性预测中更优。
尽管异质性在节点级任务中已被广泛研究，其在图级任务中的影响仍不明确。本文首次系统分析了图级学习中的异质性，结合理论与实证。我们提出图级标签方案的分类体系，聚焦局部结构标签中的模式检测任务。通过基于能量的梯度流分析，揭示关键洞见：与节点级任务中以频率为主导的格局不同，模式检测需要跨多个频谱成分的混合频率动态以保持灵活性。理论表明，模式目标与全局频率主导存在本质偏差，需采用不同的架构设计。在具有可控异质性的合成数据集及真实世界分子属性预测任务上的实验验证了该结论，显示频率自适应模型优于频率主导模型。本工作建立了图级学习中异质性的新理论认知，并为GNN架构设计提供指导。
原文摘要 · Abstract (English)
While heterophily has been widely studied in node-level tasks, its impact on graph-level tasks remains unclear. We present the first analysis of heterophily in graph-level learning, combining theoretical insights with empirical validation. We first introduce a taxonomy of graph-level labeling schemes, and focus on motif-based tasks within local structure labeling, which is a popular labeling scheme. Using energy-based gradient flow analysis, we reveal a key insight: unlike frequency-dominated regimes in node-level tasks, motif detection requires mixed-frequency dynamics to remain flexible across multiple spectral components. Our theory shows that motif objectives are inherently misaligned with global frequency dominance, demanding distinct architectural considerations. Experiments on synthetic datasets with controlled heterophily and real-world molecular property prediction support our findings, showing that frequency-adaptive model outperform frequency-dominated models. This work establishes a new theoretical understanding of heterophily in graph-level learning and offers guidance for designing effective GNN architectures.
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。