S
Shaohua Fan
Researcher at Beijing University of Posts and Telecommunications
Publications - 11
Citations - 464
Shaohua Fan is an academic researcher from Beijing University of Posts and Telecommunications. The author has contributed to research in topics: Computer science & Cluster analysis. The author has an hindex of 4, co-authored 8 publications receiving 157 citations. Previous affiliations of Shaohua Fan include Peking University.
Papers
More filters
Proceedings ArticleDOI
Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation
TL;DR: A metapath-guided heterogeneous Graph Neural Network to learn the embeddings of objects in intent recommendation as a Heterogeneous Information Network is proposed and Offline experiments on real large-scale data show the superior performance of the proposed MEIRec, compared to representative methods.
Proceedings ArticleDOI
One2Multi Graph Autoencoder for Multi-view Graph Clustering
TL;DR: This paper makes the first attempt to employ deep learning technique for attributed multi-view graph clustering, and proposes a novel task-guided One2Multi graph autoencoder clustering framework that can jointly optimize the cluster label assignments and embeddings suitable forgraph clustering.
Posted Content
A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources
TL;DR: This survey presents several widely deployed systems that have demonstrated the success of HG embedding techniques in resolving real-world application problems with broader impacts and summarizes the open-source code, existing graph learning platforms and benchmark datasets.
Proceedings ArticleDOI
Abnormal Event Detection via Heterogeneous Information Network Embedding
Shaohua Fan,Chuan Shi,Xiao Wang +2 more
TL;DR: A novel deep heterogeneous network embedding method which incorporates the entity attributes and second-order structures simultaneously to address the problem of number of co-occurrences of majority entities in events.
Proceedings ArticleDOI
Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure
TL;DR: A general disentangled GNN framework to learn the causal substructure and bias substructure, respectively is proposed, which has appealing interpretability and transferability and achieves superior generalization performance over existing baselines.