Swapping attentive GNN score mappings for a single-layer Kolmogorov-Arnold Network improves benchmark performance and, on a specially constructed input matrix, provably achieves zero maximum ranking error.
A survey on graph neural networks and graph transformers in computer vision: A task-oriented perspective
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
-
KAA: Kolmogorov-Arnold Attention for Enhancing Attentive Graph Neural Networks
Swapping attentive GNN score mappings for a single-layer Kolmogorov-Arnold Network improves benchmark performance and, on a specially constructed input matrix, provably achieves zero maximum ranking error.