4 papers · 1 filter
TopoCompile: Molecular Generation with Exact Global Count Constraints
Xiang Wu, Rong-Hua Li, Quanqing Xu +2
Molecular generation designs novel molecules with desired structures and properties. Global count constraints specify molecular size, elemental composition, and ring content withou…
Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix
Jinhao Zhang, Kangfei Zhao, Qiuhao Zeng +1
Transformer-based architectures have become the dominant paradigm for Continuous-Time Dynamic Graph (CTDG) learning, yet their performance remains limited on temporally shifted dat…
Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms
Xiang Wu, Rong-Hua Li, Xunkai Li +3
Graph coarsening reduces the size of a graph while preserving certain properties. Most existing methods preserve either spectral or spatial characteristics. Recent research shows t…
ScaDyG:A New Paradigm for Large-scale Dynamic Graph Learning
Xiang Wu, Xunkai Li, Rong-Hua Li +2
Dynamic graphs (DGs), which capture time-evolving relationships between graph entities, have widespread real-world applications. To efficiently encode DGs for downstream tasks, mos…