提出自适应图神经网络，解决异质图中异质性与异类连接共存的难题。
Adaptive Heterogeneous Graph Neural Networks: Bridging Heterophily and Heterogeneity
- 设计异类感知卷积，动态捕捉不同跳数和元路径的异类分布。
- 通过粗到细注意力机制融合多语义信息，有效过滤噪声、保留关键信号。
- 在7个真实数据集上超越20个基线模型，尤其在高异类性场景表现突出。
异质图在现实场景中普遍存在且常呈现异类连接特性。然而，现有研究多孤立关注异质性或异类连接，忽视了实际应用中异类异质图的普遍性，导致性能下降。本文首次识别出建模异类异质图的两大挑战：(1) 不同跳数和元路径间异类分布差异显著；(2) 不同元路径间语义信息复杂多样，且常由异类驱动。为此，我们提出自适应异质图神经网络（AHGNN），采用异类感知卷积，针对跳数与元路径分别建模异类分布；再通过粗到细注意力机制整合来自不同语义空间的消息，实现噪声过滤与关键信号强化。在7个真实世界图数据集及20个基线模型上的实验表明，AHGNN性能显著优于对比方法，尤其在高异类性场景下优势明显。
原文摘要 · Abstract (English)
Heterogeneous graphs (HGs) are common in real-world scenarios and often exhibit heterophily. However, most existing studies focus on either heterogeneity or heterophily in isolation, overlooking the prevalence of heterophilic HGs in practical applications. Such ignorance leads to their performance degradation. In this work, we first identify two main challenges in modeling heterophily HGs: (1) varying heterophily distributions across hops and meta-paths; (2) the intricate and often heterophily-driven diversity of semantic information across different meta-paths. Then, we propose the Adaptive Heterogeneous Graph Neural Network (AHGNN) to tackle these challenges. AHGNN employs a heterophily-aware convolution that accounts for heterophily distributions specific to both hops and meta-paths. It then integrates messages from diverse semantic spaces using a coarse-to-fine attention mechanism, which filters out noise and emphasizes informative signals. Experiments on seven real-world graphs and twenty baselines demonstrate the superior performance of AHGNN, particularly in high-heterophily situations.
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。