3 papers
cs.LG2024
Mitigating Exposure Bias in Score-Based Generation of Molecular Conformations
Sijia Wang, Chen Wang, Zhenhao Zhao +2
Molecular conformation generation poses a significant challenge in the field of computational chemistry. Recently, Diffusion Probabilistic Models (DPMs) and Score-Based Generative…
cs.LG2024
Multiplex Graph Contrastive Learning with Soft Negatives
Zhenhao Zhao, Minhong Zhu, Chen Wang +4
Graph Contrastive Learning (GCL) seeks to learn nodal or graph representations that contain maximal consistent information from graph-structured data. While node-level contrasting…
cs.LG2024
Hybrid Focal and Full-Range Attention Based Graph Transformers
Minhong Zhu, Zhenhao Zhao, Weiran Cai
The paradigm of Transformers using the self-attention mechanism has manifested its advantage in learning graph-structured data. Yet, Graph Transformers are capable of modeling full…