Structure-Aware Prototypical Neural Process for Few-Shot Graph Classification

doi:10.1109/TNNLS.2022.3173318

CSpace > 应用数学研究所

	Structure-Aware Prototypical Neural Process for Few-Shot Graph Classification
	Lin, Xixun 1,2; Li, Zhao 3,4; Zhang, Peng 5; Liu, Luchen 6; Zhou, Chuan2,7,8 ; Wang, Bin 6; Tian, Zhihong 5
	2022-05-20
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
页码	15
摘要	Graph classification plays an important role in a wide range of applications from biological prediction to social analysis. Traditional graph classification models built on graph kernels are hampered by the challenge of poor generalization as they are heavily dependent on the dedicated design of handcrafted features. Recently, graph neural networks (GNNs) become a new class of tools for analyzing graph data and have achieved promising performance. However, it is necessary to collect a large number of labeled graph data for training an accurate GNN, which is often unaffordable in real-world applications. Therefore, it is an open question to build GNNs under the condition of few-shot learning where only a few labeled graphs are available. In this article, we introduce a new Structure-aware Prototypical Neural Process (SPNP for short) for a few-shot graph classification. Specifically, at the encoding stage, SPNP first employs GNNs to capture graph structure information. Then, SPNP incorporates such structural priors into the latent path and the deterministic path for representing stochastic processes. At the decoding stage, SPNP uses a new prototypical decoder to define a metric space where unseen graphs can be predicted effectively. The proposed decoder, which contains a self-attention mechanism to learn the intraclass dependence between graphs, can enhance the class-level representations, especially for new classes. Furthermore, benefited from such a flexible encoding-decoding architecture, SPNP can directly map the context samples to a predictive distribution without any complicated operations used in previous methods. Extensive experiments demonstrate that SPNP achieves consistent and significant improvements over state-of-the-art methods. Further discussions are provided toward model efficiency and more detailed analysis.
关键词	Task analysis Kernel Training Decoding Stochastic processes Predictive models Computational modeling Few-shot learning graph classification graph neural networks (GNNs) neural process (NP)
DOI	10.1109/TNNLS.2022.3173318
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2021YFB3100600] ; NSFC[11688101] ; NSFC[61872360] ; NSFC[U20B2046] ; CAS Project for Young Scientists in Basic Research[YSBR-008] ; Guangdong Higher Education Innovation Group[2020KCXTD007] ; Guangzhou Higher Education Innovation Group[202032854] ; Alibaba Group through Alibaba Innovative Research Program
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000800781700001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/61473
专题	应用数学研究所
通讯作者	Zhang, Peng; Zhou, Chuan
作者单位	1.Chinese Acad Sci, Inst Informat Engn, Beijing 101408, Peoples R China 2.Univ Chinese Acad Sci, Sch Cyber Secur, Beijing 101408, Peoples R China 3.Zhejiang Univ, Alibaba Zhejiang Univ Joint Inst Frontier Technol, Hangzhou 310027, Peoples R China 4.Link2Do Technol Ltd, Hangzhou 311113, Peoples R China 5.Guangzhou Univ, Cyberspace Inst Adv Technol, Guangzhou 510006, Peoples R China 6.Xiaomi Inc, Xiaomi AI Lab, Beijing 100102, Peoples R China 7.Chinese Acad Sci, Acad Math & Syst Sci, Beijing 101408, Peoples R China 8.Univ Chinese Acad Sci, Acad Math & Syst Sci, Chinese Acad Sci, Also Sch Cyber Secur, Beijing 101408, Peoples R China
推荐引用方式 GB/T 7714	Lin, Xixun,Li, Zhao,Zhang, Peng,et al. Structure-Aware Prototypical Neural Process for Few-Shot Graph Classification[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022:15.
APA	Lin, Xixun.,Li, Zhao.,Zhang, Peng.,Liu, Luchen.,Zhou, Chuan.,...&Tian, Zhihong.(2022).Structure-Aware Prototypical Neural Process for Few-Shot Graph Classification.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,15.
MLA	Lin, Xixun,et al."Structure-Aware Prototypical Neural Process for Few-Shot Graph Classification".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022):15.