5 papers
GraphSculptor: Sculpting Pre-training Coreset for Graph Self-supervised Learning
Chuang Liu, Zelin Yao, Xueqi Ma +4
Graph self-supervised learning typically relies on large-scale unlabeled datasets, heavily inflating computational costs. However, empirical evidence suggests that these datasets c…
Hi-GMAE: Hierarchical Graph Masked Autoencoders
Chuang Liu, Zelin Yao, Xueqi Ma +4
Graph Masked Autoencoders (GMAEs) have emerged as a notable self-supervised learning approach for graph-structured data. Existing GMAE models primarily focus on reconstructing node…
Dual-perspective Cross Contrastive Learning in Graph Transformers
Zelin Yao, Chuang Liu, Xueqi Ma +5
Graph contrastive learning (GCL) is a popular method for leaning graph representations by maximizing the consistency of features across augmented views. Traditional GCL methods uti…
Where to Mask: Structure-Guided Masking for Graph Masked Autoencoders
Chuang Liu, Yuyao Wang, Yibing Zhan +4
Graph masked autoencoders (GMAE) have emerged as a significant advancement in self-supervised pre-training for graph-structured data. Previous GMAE models primarily utilize a strai…
Gradformer: Graph Transformer with Exponential Decay
Chuang Liu, Zelin Yao, Yibing Zhan +3
Graph Transformers (GTs) have demonstrated their advantages across a wide range of tasks. However, the self-attention mechanism in GTs overlooks the graph's inductive biases, parti…