哈格恩:对异质图神经网络的混合聚合
概括
异质图形神经网络 (GNN) 现在可以利用meta-path和meta-path-free方法. 拟议的混合聚合异质GNN (HAGNN) 框架有效地将这些方法结合起来,以提高性能.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 图形神经网络的神经网络
背景情况:
- 不同质的图形神经网络 (GNN) 对于处理复杂的图形数据是有效的.
- 在现有的异质GNN中,元路径至关重要,但它们的必要性仍在争论中.
- 没有元路径的模型显示了可比性能,质疑对元路径的完全依赖.
研究的目的:
- 研究GNN中基于元路径和无元路径的邻居选择之间的内在差异.
- 为全面的语义信息利用提出一种新的框架,即异质GNN的混合聚合 (HAGNN).
- 通过同时利用元路径和直接连接的邻居来增强异构的GNN.
主要方法:
- HAGNN采用了两阶段的聚合:基于元路径的内部类型和无元路径的类型间聚合.
- 为结构性语义意识聚合引入了一个融合的元路径图形数据结构.
- 两个聚合阶段的嵌入组合在一起,以捕捉丰富的图形语义.
主要成果:
- 通过结合不同的聚合策略,HAGNN有效地利用图形的异质性.
- 对节点分类,集群和链接预测的实验证明了HAGNN的优势.
- 拟议的框架显示了与现有的异质GNN模型相比的显著改进.
结论:
- 哈格恩提供了一种全面的方法来学习异质图表表示.
- 该框架有效地整合了多样化的语义信息,优于现有的方法.
- 在各种基于图表的任务中,HAGNN表现出更高的有效性和效率.
相关概念视频
Hybrid Zones
16.7K
Hybrid zones are narrow regions where two closely related species interact, mate, and produce hybrids. Relative to either parent species, hybrids may possess distinct phenotypic or genetic differences that impact their survival and reproductive success. The genetic variances introduced by hybridization influence species diversity and speciation processes within the hybrid zone.
16.7K
Hybridization of Atomic Orbitals II
31.6K
sp3d and sp3d 2 Hybridization
31.6K
Neural Circuits
974
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
974


