1 code repository containing implementation scripts for the ICLR 2021 paper 'Analyzing the Expressive Power of Graph Neural Networks in a Spectral Perspective'. It provides the computational framework for evaluating the expressive power of graph neural networks through spectral filter analysis.
Use Cases
- Reproduce the spectral expressive power benchmarks using the provided ICLR 2021 code
- Analyze GNN models using the spectral perspective framework
- Evaluate the expressive power of graph networks using the provided implementation
Strengths
- Official code for the ICLR 2021 paper 'Analyzing the Expressive Power of Graph Neural Networks in a Spectral Perspective'
- Implementation of spectral analysis techniques for Graph Neural Networks
- Framework for evaluating the expressive power of graph-based models