AI RESEARCH
LEAP: Local ECT-Based Learnable Positional Encodings for Graphs
arXiv CS.LG
•
ArXi:2510.00757v3 Announce Type: replace Graph neural networks (GNNs) largely rely on the message-passing paradigm, where nodes iteratively aggregate information from their neighbors. Yet, standard message passing neural networks (MPNNs) face well-documented theoretical and practical limitations. Graph positional encoding (PE) has emerged as a promising direction to address these limitations. The Euler Characteristic Transform (ECT) is an efficiently computable geometric-topological invariant that characterizes shapes and graphs.