6 papers
Information-Theoretic Limits of Node Localization under Hybrid Graph Positional Encodings
Zimo Yan, Zheng Xie, Chang Liu +2
Positional encoding has become a standard component in graph learning, especially for graph Transformers and other models that must distinguish structurally similar nodes, yet its…
Bridging Distance and Spectral Positional Encodings via Anchor-Based Diffusion Geometry Approximation
Zimo Yan, Zheng Xie, Runfan Duan +2
Molecular graph learning benefits from positional signals that capture both local neighborhoods and global topology. Two widely used families are spectral encodings derived from La…
Resolving Node Identifiability in Graph Neural Processes via Laplacian Spectral Encodings
Zimo Yan, Zheng Xie, Chang Liu +1
Message passing graph neural networks are widely used for learning on graphs, yet their expressive power is limited by the one-dimensional Weisfeiler-Lehman test and can fail to di…
A Multi-Scale Graph Neural Process with Cross-Drug Co-Attention for Drug-Drug Interactions Prediction
Zimo Yan, Jie Zhang, Zheng Xie +2
Accurate prediction of drug-drug interactions (DDI) is crucial for medication safety and effective drug development. However, existing methods often struggle to capture structural…
Higher-order Network phenomena of cascading failures in resilient cities
Jinghua Song, Yuan Wang, Zimo Yan
Modern urban resilience is threatened by cascading failures in multimodal transport networks, where localized shocks trigger widespread paralysis. Existing models, limited by their…
MetaMolGen: A Neural Graph Motif Generation Model for De Novo Molecular Design
Zimo Yan, Jie Zhang, Zheng Xie +3
Molecular generation plays an important role in drug discovery and materials science, especially in data-scarce scenarios where traditional generative models often struggle to achi…