S
Shirui Pan
Researcher at Monash University
Publications - 187
Citations - 14539
Shirui Pan is an academic researcher from Monash University. The author has contributed to research in topics: Computer science & Graph (abstract data type). The author has an hindex of 36, co-authored 151 publications receiving 7202 citations. Previous affiliations of Shirui Pan include University of Technology, Sydney & Northwest A&F University.
Papers
More filters
Posted Content
Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning
TL;DR: A novel GCN-based SSL algorithm is presented in this paper to enrich the supervision signals by utilizing both data similarities and graph structure, and the underlying determinative relationship between the data features and input graph topology is extracted via using a graph generative loss related to the input features.
Proceedings ArticleDOI
Multi-graph-view Learning for Graph Classification
TL;DR: A Cross Graph-View Sub graph Feature based Learning (gCGVFL) algorithm that explores an optimal set of sub graphs, across multiple graph-views, as features to represent graphs for multi-graph-view learning.
Proceedings ArticleDOI
Relation Structure-Aware Heterogeneous Graph Neural Network
TL;DR: Experiments and comparisons, based on semi-supervised classification tasks on large scale heterogeneous networks with over a hundred types of edges, show that RSHN significantly outperforms state-of-the-arts.
Proceedings Article
Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning.
TL;DR: Zhang et al. as mentioned in this paper proposed a GCN-based semi-supervised learning (SSL) algorithm which aims to enrich the supervision signals by utilizing both data similarities and graph structure.
Journal ArticleDOI
Exploiting Attribute Correlations: A Novel Trace Lasso-Based Weakly Supervised Dictionary Learning Method
Lin Wu,Yang Wang,Shirui Pan +2 more
TL;DR: This paper proposes a weakly-supervised dictionary learning method to automatically learn a discriminative dictionary by fully exploiting visual attribute correlations rather than label priors, and then a set of subdictionaries are jointly learned with respect to each category.