Back to publications
GRANOLA: Adaptive Normalization for Graph Neural Networks
Paper Details
Published: 2024/10/31
DOI: 10.48550/arXiv.2404.13344
ARXIV ID: 2404.13344v2
Despite their widespread adoption, the incorporation of off-the-shelf normalization layers within a GNN architecture may not effectively capture the unique characteristics of graph-structured data, potentially reducing the expressive power of the overall architecture. The authors propose GRANOLA, a novel graph-adaptive normalization layer. Unlike existing normalization layers, GRANOLA normalizes node features by adapting to the specific characteristics of the graph, particularly by generating expressive representations of its neighborhood structure, obtained by leveraging the propagation of Random Node Features (RNF) in the graph. Extensive empirical evaluation of various graph benchmarks underscores the superior performance of GRANOLA over existing normalization techniques.
Authors
B. Bevilacqua
C.B. Schonlieb