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
Journal ArticleDOI
Geometry Contrastive Learning on Heterogeneous Graphs
TL;DR: Geometry Contrastive Learning (GCL) as discussed by the authors proposes a self-supervised learning method to better represent the heterogeneous graphs when supervisory data is unavailable, which maximizes the mutual information between two geometric views by contrasting representations at both local-local and local-global semantic levels.
Dissertation
Complex graph stream mining
TL;DR: A novel algorithm is proposed, CGStream, to identify correlated graphs from a data stream, by using a sliding window, which covers a number of consecutive batches of stream data records, and experimental results demonstrate that the proposed algorithm is several times, or even an order of magnitude, more efficient than the straightforward algorithms.
Journal ArticleDOI
How heterogeneous social influence acts on human decision-making in online social networks
TL;DR: In this paper , the authors investigate the patterns of heterogeneous social influence on human decision-making from the perspectives of opinions, behaviors, preferences and decision probabilities across three large-scale online networks.
Proceedings ArticleDOI
CurvDrop: A Ricci Curvature Based Approach to Prevent Graph Neural Networks from Over-Smoothing and Over-Squashing
TL;DR: Yang et al. as discussed by the authors proposed a new Curvature-based topology-aware dropout sampling technique named CurvDrop, in which they integrate the Discrete RicciCurvature into graph neural networks to enable more expressive graph models.
Posted Content
iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients
TL;DR: In this paper, a stochastic hypergradient approximation for differentiable NAS is proposed, and theoretically show that the architecture optimization with the proposed method, named iDARTS, is expected to converge to a stationary point, making it only depend on the obtained solution to the inner-loop optimization and agnostic to the optimization path.