In contextual stochastic block models, graph attention improves node classification when structure noise dominates feature noise, but plain convolution is better in the opposite regime, and multi-layer attention achieves perfect classification with SNR as low as ω(√log n/n^{1/3}).
An iterative clustering algorithm for the contextual stochastic block model with optimality guarantees
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models
In contextual stochastic block models, graph attention improves node classification when structure noise dominates feature noise, but plain convolution is better in the opposite regime, and multi-layer attention achieves perfect classification with SNR as low as ω(√log n/n^{1/3}).