3 papers
cs.LG2026
Converse and Collision-Based Achievability for Node Localization with Hybrid Distance-Spectral Graph Positional Encodings
Zimo Yan, Yifan Li, Hao Li +4
Graph positional encodings are widely used in graph neural networks and graph Transformers, yet it remains unclear when the code itself can identify nodes. We study a hybrid distan…
cs.IT2026
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…
cs.LG2025
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…