Searching to extrapolate embedding for out-of-graph node representation learning

doi:10.1016/j.neunet.2024.107118

	Searching to extrapolate embedding for out-of-graph node representation learning
	Shen, Zhenqian 1; Guo, Shuhan 1; Wen, Yan 1; Wei, Lanning 2; Zhang, Wengang 3; Luo, Yuanhai 3; Wu, Chongwu 3; Yao, Quanming 1
	2025-04-01
发表期刊	NEURAL NETWORKS
ISSN	0893-6080
卷号	184 页码:15
摘要	Out-of-graph node representation learning aims at learning about newly arrived nodes fora dynamic graph. It has wide applications ranging from community detection, recommendation system to malware detection. Although existing methods can be adapted for out-of-graph node representation learning, real-world challenges such as fixed in-graph node embedding and data diversity essentially limit the performance of these methods. Here, we formulate the problem as a neural architecture search problem, and propose searching to extrapolate embedding (S2E), a solution that extrapolates embedding for out-of-graph nodes according to their neighbor node embeddings. Firstly, we propose an embedding extrapolating framework containing multiple transition modules and an aggregation module to handle fixed in-graph node embedding for embedding extrapolation. To deal with data diversity, we propose searching extrapolating architecture, where we employ objective transformation to handle non-differentiable evaluation metric and make neural architecture search procedure more efficient. In experiments, we show that S2E achieves outstanding performance in real-world datasets. We further conduct experiments on the proposed search space and search algorithm to verify the effectiveness of our design in S2E.
关键词	Graph neural network Neural architecture search Graph embedding Out-of-sample learning
DOI	10.1016/j.neunet.2024.107118
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Neurosciences & Neurology
WOS类目	Computer Science, Artificial Intelligence ; Neurosciences
WOS记录号	WOS:001398058900001
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40795
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Yao, Quanming
作者单位	1.Tsinghua Univ, Dept Elect Engn, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Inst Comp Technol, Chinese Acad Sci, Beijing, Peoples R China 3.OPPO Res, Dongguan, Peoples R China
推荐引用方式 GB/T 7714	Shen, Zhenqian,Guo, Shuhan,Wen, Yan,et al. Searching to extrapolate embedding for out-of-graph node representation learning[J]. NEURAL NETWORKS,2025,184:15.
APA	Shen, Zhenqian.,Guo, Shuhan.,Wen, Yan.,Wei, Lanning.,Zhang, Wengang.,...&Yao, Quanming.(2025).Searching to extrapolate embedding for out-of-graph node representation learning.NEURAL NETWORKS,184,15.
MLA	Shen, Zhenqian,et al."Searching to extrapolate embedding for out-of-graph node representation learning".NEURAL NETWORKS 184(2025):15.