Liangrui Wu

Liangrui Wu

Auto-generated profile, based on publicly available information

Liangrui Wu

Shanghai University

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
6 April 2024 in Knowledge and Information Systems
Verified
Journal Article
Closed access
PDF file
HLHehe Lv
Hehe Lv
GZGuobing Zou
Guobing Zou
BZBofeng Zhang
Bofeng Zhang
SHShengxiang Hu
Shengxiang Hu
CZChenyang Zhou
Chenyang Zhou
LWLiangrui Wu
Liangrui Wu

30 August 2022 in Entropy
Verified
Journal Article
Open access
PDF file
SHShengxiang Hu
Shengxiang Hu
BZBofeng Zhang
Bofeng Zhang
HLHehe Lv
Hehe Lv
HWHaochen Wang
Haochen Wang
CZChenyang Zhou
Chenyang Zhou
GZGuobing Zou
Guobing Zou
Network data analysis is a crucial method for mining complicated object interactions. In recent years, random walk and neural-language-model-based network representation learning (NRL) approaches have been widely used for network data analysis. However, these NRL approaches suffer from the following deficiencies: firstly, because the random walk procedure is based on symmetric node similarity and fixed probability distribution, the sampled vertices’ sequences may lose local community structure information; secondly, because the feature extraction capacity of the shallow neural language model is limited, they can only extract the local structural features of networks; and thirdly, these approaches require specially designed mechanisms for different downstream tasks to integrate vertex attributes of various types. We conducted an in-depth investigation to address the aforementioned issues and propose a novel general NRL framework called dynamic structure and vertex attribute fusion network embedding, which firstly defines an asymmetric similarity and h-hop dynamic random walk strategy to guide the random walk process to preserve the network’s local community structure in walked vertex sequences. Next, we train a self-attention-based sequence prediction model on the walked vertex sequences to simultaneously learn the vertices’ local and global structural features. Finally, we introduce an attributes-driven Laplacian space optimization to converge the process of structural feature extraction and attribute feature extraction. The proposed approach is exhaustively evaluated by means of node visualization and classification on multiple benchmark datasets, and achieves superior results compared to baseline approaches.

25 April 2024
Verified
Book Chapter
Closed access
PDF file
CZChenyang Zhou
Chenyang Zhou
GZGuobing Zou
Guobing Zou
SHShengxiang Hu
Shengxiang Hu
HLHehe Lv
Hehe Lv
LWLiangrui Wu
Liangrui Wu
BZBofeng Zhang
Bofeng Zhang