Logic-based Weisfeiler-Leman variants enable graph-to-table conversion for classification that matches GNN and graph transformer accuracy while running 5-20x faster without GPUs.
We can thus compute the finite set of computable quantifiersQ0 ⊆ Q associated with the effective representationf such that Q0 := f(k)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Graph Learning via Logic-Based Weisfeiler-Leman Variants and Tabularization
Logic-based Weisfeiler-Leman variants enable graph-to-table conversion for classification that matches GNN and graph transformer accuracy while running 5-20x faster without GPUs.