Y
Yixin Liu
Researcher at Monash University, Clayton campus
Publications - 15
Citations - 298
Yixin Liu is an academic researcher from Monash University, Clayton campus. The author has contributed to research in topics: Computer science & Graph (abstract data type). The author has an hindex of 3, co-authored 6 publications receiving 33 citations. Previous affiliations of Yixin Liu include Monash University.
Papers
More filters
Journal ArticleDOI
Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
TL;DR: In this article, a contrastive self-supervised learning framework for anomaly detection on attributed networks is proposed, which exploits the local information from network data by sampling a novel type of contrastive instance pair, which can capture the relationship between each node and its neighboring substructure.
Journal Article
Graph Neural Networks for Graphs with Heterophily: A Survey
TL;DR: A systematic taxonomy that essentially governs existing heterophilic GNN models is proposed, along with a general summary and detailed analysis, to facilitate robust and fair evaluations of these graph neural networks.
Posted Content
Graph Self-Supervised Learning: A Survey
TL;DR: In this paper, the authors present a comprehensive review of graph self-supervised learning (SSL) techniques for graph data and present a unified framework that mathematically formalizes the paradigm of graph SSL.
Proceedings ArticleDOI
Towards Unsupervised Deep Graph Structure Learning
TL;DR: A novel StrUcture Bootstrapping contrastive LearnIng fraMEwork (SUBLIME for abbreviation) with the aid of self-supervised contrastive learning is proposed, where the learned graph topology is optimized by data itself without any external guidance.
Journal ArticleDOI
Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection
TL;DR: Li et al. as discussed by the authors proposed a self-supervised learning for graph anomaly detection (SL-GAD), which constructs different contextual subgraphs (views) based on a target node and employs two modules, generative attribute regression and multi-view contrastive learning for anomaly detection.