14 citations · 19 across the 7 of their papers we have counts for
7 papers
Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detection
Yunhui Liu, Jiashun Cheng, Yiqing Lin +7
Graph anomaly detection (GAD) has garnered increasing attention in recent years, yet remains challenging due to two key factors: (1) label scarcity stemming from the high cost of a…
Learning Accurate, Efficient, and Interpretable MLPs on Multiplex Graphs via Node-wise Multi-View Ensemble Distillation
Yunhui Liu, Zhen Tao, Xiang Zhao +3
Multiplex graphs, with multiple edge types (graph views) among common nodes, provide richer structural semantics and better modeling capabilities. Multiplex Graph Neural Networks (…
Negative-Free Self-Supervised Gaussian Embedding of Graphs
Yunhui Liu, Tieke He, Tao Zheng +1
Graph Contrastive Learning (GCL) has recently emerged as a promising graph self-supervised learning framework for learning discriminative node representations without labels. The w…
Teaching MLPs to Master Heterogeneous Graph-Structured Knowledge for Efficient and Accurate Inference
Yunhui Liu, Xinyi Gao, Tieke He +2
Heterogeneous Graph Neural Networks (HGNNs) have achieved promising results in various heterogeneous graph learning tasks, owing to their superiority in capturing the intricate rel…
Scalable and Adaptive Spectral Embedding for Attributed Graph Clustering
Yunhui Liu, Tieke He, Qing Wu +2
Attributed graph clustering, which aims to group the nodes of an attributed graph into disjoint clusters, has made promising advancements in recent years. However, most existing me…
Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning
Yunhui Liu, Huaisong Zhang, Tieke He +2
Contrastive learning is a significant paradigm in graph self-supervised learning. However, it requires negative samples to prevent model collapse and learn discriminative represent…