A New Perspective on the Effects of Spectrum in Graph Neural Networks

2021/12/14 by Mingqi Yang, Yang, Mingqi, Yanming Shen +9 · 2 citations
Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Complex Network Analysis Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2112.07160

openalex publication_date 2021/12/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Many improvements on GNNs can be deemed as operations on the spectrum of the underlying graph matrix, which motivates us to directly study the characteristics of the spectrum and their effects on GNN performance. By generalizing most existing GNN architectures, we show that the correlation issue caused by the unsmooth spectrum becomes the obstacle to leveraging more powerful graph filters as well as developing deep architectures, which therefore restricts GNNs' performance. Inspired by this, we propose the correlation-free architecture which naturally removes the correlation issue among different channels, making it possible to utilize more sophisticated filters within each channel. The final correlation-free architecture with more powerful filters consistently boosts the performance of learning graph representations. Code is available at https://github.com/qslim/gnn-spectrum.

Cited by

• Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogramming
• Toward Data-centric Directed Graph Learning: An Entropy-driven Approach

Related

• Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective
• A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness
• Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks
• GrassNet: State Space Model Meets Graph Neural Network
• How Powerful are Spectral Graph Neural Networks