Invariant-Stratified Propagation (ISP) enhances GNN expressivity beyond 1-WL by stratifying nodes according to graph invariants and encoding structural heterogeneity in hierarchical strata.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A new interference modeling approach with partial attentions and message amplification captures varying neighbor importance and scale to improve ITE estimation on graphs.
citing papers explorer
-
Invariant-Stratified Propagation for Expressive Graph Neural Networks
Invariant-Stratified Propagation (ISP) enhances GNN expressivity beyond 1-WL by stratifying nodes according to graph invariants and encoding structural heterogeneity in hierarchical strata.
-
Treatment Effect Estimation with Differentiated Networked Effect on Graph Data
A new interference modeling approach with partial attentions and message amplification captures varying neighbor importance and scale to improve ITE estimation on graphs.