Adaptive Neighbor Graph Aggregated Graph Attention Network for Heterogeneous Graph Embedding
ACM Transactions on Knowledge Discovery from Data · 31.01.2024 · 18 (1) · 1-21
DOI: 10.1145/3616377 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Knowledge Discovery from Data, online erschienen am 16.10.2023. Verfasst von Lin Kaibiao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Xiamen City, China, National Key R&D Program of China.
Abstract (Originalsprache)
Graph attention network can generate effective feature embedding by specifying different weights to different nodes. The key of the research on heterogeneous graph embedding is the way to combine its rich structural information with semantic relations to aggregate the neighborhood information. Most of the existing heterogeneous graph representation learning methods guide the selection of neighbors by defining various meta-paths on heterogeneous graphs. However, these models only consider the information contained in the nodes under different paths and ignore the potential semantic relationships of nodes in different neighbor graph structures, which leads to the underutilization of graph structure information. In this article, we propose a novel adaptive framework named Neighbor Graph Aggregated Graph Attention Network (NGGAN) to fully exploit graph topological details in heterogeneous graph, and aggregates their information to obtain an effective embedding. The key idea is to use different levels of sampling methods to define neighborhood, and use neighbor graphs to represent the complex structural interaction between nodes. In this way, the high-order relationship between nodes and the latent semantics of neighbor graphs can be fully explored. Afterward, a hierarchical attention mechanism is applied to adaptively learn the importance of different objects, including node information, path information, and neighbor graph information. Multiple downstream tasks are performed on four real-world heterogeneous graph datasets, and the experimental results demonstrate the effectiveness of NGGAN.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Xiamen City, China
- National Key R&D Program of China
- Science Foundation of Fujian Province
Zitieren
APA
Kaibiao, L., Chen, J., Ruicong, C., Fan, Y., Yang, Z., Min, L., & Ping, L. (2024). Adaptive Neighbor Graph Aggregated Graph Attention Network for Heterogeneous Graph Embedding. ACM Transactions on Knowledge Discovery from Data, 18(1), 1-21. https://doi.org/10.1145/3616377
Vancouver
Kaibiao L, Chen J, Ruicong C, Fan Y, Yang Z, Min L, et al. Adaptive Neighbor Graph Aggregated Graph Attention Network for Heterogeneous Graph Embedding. ACM Transactions on Knowledge Discovery from Data. 2024;18(1):1-21. doi:10.1145/3616377
BibTeX
@article{Kaibiao2024,
author = {Kaibiao, Lin and Chen, Jinpo and Ruicong, Chen and Fan, Yang and Yang, Zhang and Min, Lin and Ping, Lu},
title = {Adaptive Neighbor Graph Aggregated Graph Attention Network for Heterogeneous Graph Embedding},
journal = {ACM Transactions on Knowledge Discovery from Data},
year = {2024},
volume = {18},
number = {1},
pages = {1--21},
doi = {10.1145/3616377}
}
EUVIMED