Truncation causes different positional encoding families to have unequal expressive power in GNNs, with truncated spectral PEs limited to 1-WL strength, and mixing families improves results on real datasets.
Title resolution pending
2 Pith papers cite this work, alongside 331 external citations. Polarity classification is still indexing.
2
Pith papers citing it
331
external citations · OpenAlex
years
2026 2verdicts
UNVERDICTED 2representative citing papers
An algorithm exploits the near-Sylvester structure of meeting time equations to compute all pairwise expected meeting times on graphs in O(N^4) operations.
citing papers explorer
-
Understanding Truncated Positional Encodings for Graph Neural Networks
Truncation causes different positional encoding families to have unequal expressive power in GNNs, with truncated spectral PEs limited to 1-WL strength, and mixing families improves results on real datasets.
-
Meeting times on graphs in near-cubic time
An algorithm exploits the near-Sylvester structure of meeting time equations to compute all pairwise expected meeting times on graphs in O(N^4) operations.