CSGNN encodes chordless cycles and paths as structural features and is claimed to strictly outperform k-hop GNNs in expressiveness with polynomial complexity.
An end-to-end attention-based approach for learning on graphs, 2024
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
-
Chordless Structure: A Pathway to Simple and Expressive GNNs
CSGNN encodes chordless cycles and paths as structural features and is claimed to strictly outperform k-hop GNNs in expressiveness with polynomial complexity.