In dynamic node classification, GCN discriminative power is characterized by the probability that a node's future label matches its neighbors' current labels, which the authors formalize as dynamic homophily.
Beyond homophily in graph neural networks: Current limitations and effective designs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Understanding GNNs and Homophily in Dynamic Node Classification
In dynamic node classification, GCN discriminative power is characterized by the probability that a node's future label matches its neighbors' current labels, which the authors formalize as dynamic homophily.