2 papers
cs.LG2025
Understanding InfoNCE: Transition Probability Matrix Induced Feature Clustering
Ge Cheng, Shuo Wang, Yun Zhang
Contrastive learning has emerged as a cornerstone of unsupervised representation learning across vision, language, and graph domains, with InfoNCE as its dominant objective. Despit…
cs.LG2025
GEN: A Practical Alternative to Graph Transformers for Long-Range Graph Modeling
Shuo Wang, Ge Cheng, Yun Zhang
Message Passing Neural Networks (MPNNs) model local relations effectively but struggle to propagate information over long distances. Graph Transformers (GTs) mitigate this via glob…