Huidong Wu

Huidong Wu

Auto-generated profile, based on publicly available information

Huidong Wu

Institutes of Science and Development, Chinese Academy of Sciences, China; School of Public Policy and Management, University of Chinese Academy of Sciences, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 October 2024 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
Dengsheng WuDengsheng Wu
Dengsheng Wu
HWHuidong Wu
Huidong Wu
JLJianping Li
Jianping Li
Graph Neural Networks (GNNs) have gained attention for their ability in capturing node interactions to generate node representations. However, their performances are frequently restricted in real-world directed networks with natural hierarchical structures. Most current GNNs incorporate information from immediate neighbors or within predefined receptive fields, potentially overlooking long-range dependencies inherent in hierarchical structures. They also tend to neglect node adaptability, which varies based on their positions. To address these limitations, we propose a new model called Hierarchy-Aware Adaptive Graph Neural Network (HAGNN) to adaptively capture hierarchical long-range dependencies. Technically, HAGNN creates a hierarchical structure based on directional pair-wise node interactions, revealing underlying hierarchical relationships among nodes. The inferred hierarchy helps to identify certain key nodes, named Source Hubs in our research, which serve as hierarchical contexts for individual nodes. Shortcuts adaptively connect these Source Hubs with distant nodes, enabling efficient message passing for informative long-range interactions. Through comprehensive experiments across multiple datasets, our proposed model outperforms several baseline methods, thus establishing a new state-of-the-art in performance. Further analysis demonstrates the effectiveness of our approach in capturing relevant adaptive hierarchical contexts, leading to improved and explainable node representation.

1 January 2026 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
HWHuidong Wu
Huidong Wu
Dengsheng WuDengsheng Wu
Dengsheng Wu
MWMaolin Wang
Maolin Wang
HYHaoran Yang
Haoran Yang
XZXiangyu Zhao
Xiangyu Zhao
JLJianping Li
Jianping Li

18 February 2020 in Modern Physics Letters B
Verified
Journal Article
Closed access
PDF file
HWHui-Dong Wu
Hui-Dong Wu
HCHaobin Cao
Haobin Cao
YWYutong Wang
Yutong Wang
GYGuan Yan
Guan Yan

10 December 2025 in Journal of Information Science
Verified
Journal Article
Closed access
QSQiudan Su
Qiudan Su
HWHuidong Wu
Huidong Wu
JLJing Li
Jing Li
Dengsheng WuDengsheng Wu
Dengsheng Wu
Journal ratings can reflect the quality of a journal and serve as a crucial reference for evaluating scientific research outcomes. To integrate the preferences of journal rating lists proposed by different institutions, some journal evaluation integration methods have been proposed, with the Weighted Average Percentage (WAP) method being a typical representative. However, the WAP method ignores the level interval information in the rating. To address this issue, we propose the Weighted Average Interval Percentile (WAIP) method. This approach introduces information about journal grade intervals and classifies journals by integrating evaluation rules based on upper and lower bounds. In an empirical study of four well-known journals in the field of economic management, the WAIP method demonstrates its effectiveness and wide applicability, enabling more accurate and stable integration of multiple journal ranking lists. This method aims to provide a more objective perspective for journal ratings, thereby enhancing the fairness and efficiency of the evaluation process.

12 April 2026
Verified
Conference Paper
Open access
HWHuidong Wu
Huidong Wu
HXHaojia Xiang
Haojia Xiang
JGJingtong Gao
Jingtong Gao
XZXiangyu Zhao
Xiangyu Zhao
Dengsheng WuDengsheng Wu
Dengsheng Wu
JLJianping Li
Jianping Li