GNNs can produce frequency components absent from their input, so their spectral behavior is not dominated by the aggregation filter, and a new benchmark quantifies this across 14 models.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective
GNNs can produce frequency components absent from their input, so their spectral behavior is not dominated by the aggregation filter, and a new benchmark quantifies this across 14 models.