PiPE combines positional encodings with persistent homology features in a message-passing framework and is claimed to be provably more expressive than either approach alone, with empirical gains on molecular benchmarks.
Related works Graph positional encodings.Positional encodings enhance representations in Graph Neural Networks (GNNs) (Gilmer et al., 2017; Xu et al., 2019; Velickovic et al.,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Positional Encoding meets Persistent Homology on Graphs
PiPE combines positional encodings with persistent homology features in a message-passing framework and is claimed to be provably more expressive than either approach alone, with empirical gains on molecular benchmarks.