CondPSE: A Polynomial-Filtered Structural Encoder with Conditional Modulation for Graphs

arXiv:2607.25169v1 Announce Type: new Abstract: Message-passing graph neural networks are bounded by the 1-WL test and can miss topological structure that distinguishes non-isomorphic graphs. Positional and structural encodings (PSE) inject such topology-derived signals, and learned PSE encoders such as GPSE pretrain a single encoder to produce these signals from random node probes, which can then be frozen and reused as inputs across downstream graph models. We present CondPSE, a learned PSE en...