The paper reports state-of-the-art node classification on five of six tested datasets using multi-scale products of a directed adjacency matrix, but the claimed scale invariance is not rigorously demonstrated.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
ScaleNet: Scale Invariance Learning in Directed Graphs
The paper reports state-of-the-art node classification on five of six tested datasets using multi-scale products of a directed adjacency matrix, but the claimed scale invariance is not rigorously demonstrated.