activity
20232026
most citedGenerative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning

2 citations · 2 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

Text-attributed Graph Condensation via Text Selection and Attribute Matching

Haowei Han, Yuxiang Wang, Guojia Wan +5

Text-Attributed Graph (TAG) is an important type of graph structured data, where each node has a text description. TAG models usually train a Graph Neural Network (GNN) and languag…

cs.LG2023★ 2 cited

Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning

Yuxiang Wang, Xiao Yan, Chuang Hu +5

For graph self-supervised learning (GSSL), masked autoencoder (MAE) follows the generative paradigm and learns to reconstruct masked graph edges or node features. Contrastive Learn…