Shengyin Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Shengyin Sun has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Chen Ma
City University of Hong Kong
1 shared publication - Jiehao Chen
School of Software Beijing Institute of Technology Beijing 100081 China
1 shared publication - Jun Liu
University of Science and Technology of China, Hefei, China
1 shared publication - Tao Jian
Research Institute of Information Fusion Naval Aviation University Yantai Shandong China
1 shared publication - Weijian Liu
Wuhan Electronic Information Institute, Wuhan, China
1 shared publication
Latest Publications
- Open Access
- 21 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (1) , 1-26
PHE: Structure and Semantic Enhanced Pre-Training of Graph Neural Networks for Large-Scale Heterogeneous Graphs
In recent years, Graph Neural Networks (GNNs) have facilitated the development of graph data mining. However, training GNNs requires sufficient labeled task-specific data, which is expensive and sometimes unavailable. To be less dependent on labeled data, recent studies propose to pre-train GNNs in a self-supervised manner and then apply the pre-trained GNNs to downstream tasks with limited labeled data. However, most existing methods are designed solely for homogeneous graphs (real-world graphs are mostly heterogeneous) and do not consider semantic mismatch (the semantic difference between the original data and the ideal data containing more transferable semantic information). In this article, we propose an effective framework to pre-train GNNs on the large-scale heterogeneous graph. We first design a structure-aware pre-training task, which aims to capture structural properties in heterogeneous graphs. Then, we design a semantic-aware pre-training task to tackle the mismatch. Specifically, we construct a perturbation subspace composed of semantic neighbors to help deal with the semantic mismatch. Semantic neighbors make the model focus more on the general knowledge in the semantic space, which in turn assists the model in learning knowledge with better transferability. Finally, extensive experiments are conducted on real-world large-scale heterogeneous graphs to demonstrate the superiority of the proposed method over state-of-the-art baselines. Code available at https://github.com/sunshy-1/PHE .
- 21 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (1) , 1-26
Open AccessPHE: Structure and Semantic Enhanced Pre-Training of Graph Neural Networks for Large-Scale Heterogeneous Graphs
In recent years, Graph Neural Networks (GNNs) have facilitated the development of graph data mining. However, training GNNs requires sufficient labeled task-specific data, which is expensive and sometimes unavailable. To be less dependent on labeled data, recent studies propose to pre-train GNNs in a self-supervised manner and then apply the pre-trained GNNs to downstream tasks with limited labeled data. However, most existing methods are designed solely for homogeneous graphs (real-world graphs are mostly heterogeneous) and do not consider semantic mismatch (the semantic difference between the original data and the ideal data containing more transferable semantic information). In this article, we propose an effective framework to pre-train GNNs on the large-scale heterogeneous graph. We first design a structure-aware pre-training task, which aims to capture structural properties in heterogeneous graphs. Then, we design a semantic-aware pre-training task to tackle the mismatch. Specifically, we construct a perturbation subspace composed of semantic neighbors to help deal with the semantic mismatch. Semantic neighbors make the model focus more on the general knowledge in the semantic space, which in turn assists the model in learning knowledge with better transferability. Finally, extensive experiments are conducted on real-world large-scale heterogeneous graphs to demonstrate the superiority of the proposed method over state-of-the-art baselines. Code available at https://github.com/sunshy-1/PHE .
- 1 March 2021
- Published by Elsevier in Signal Processing
- Vol. 180, 107801
Robust detection of distributed targets based on Rao test and Wald test
- 1 March 2021
- Published by Elsevier in Signal Processing
- Vol. 180, 107801
Robust detection of distributed targets based on Rao test and Wald test