MLLGSep 24, 2022

From Local to Global: Spectral-Inspired Graph Neural Networks

arXiv:2209.12054v316 citationsh-index: 33
Originality Incremental advance
AI Analysis

This work addresses performance issues in graph neural networks for non-Euclidean data, particularly for heterophilous graphs, though it appears incremental as it builds on existing MPNNs with a new normalization method.

The paper tackled the limitations of message-passing graph neural networks (MPNNs) in capturing long-range signals and handling heterophilous graphs, proposing PowerEmbed, a normalization technique that provably expresses top eigenvectors to prevent over-smoothing and over-squashing, and demonstrated competitive performance on various graphs.

Graph Neural Networks (GNNs) are powerful deep learning methods for Non-Euclidean data. Popular GNNs are message-passing algorithms (MPNNs) that aggregate and combine signals in a local graph neighborhood. However, shallow MPNNs tend to miss long-range signals and perform poorly on some heterophilous graphs, while deep MPNNs can suffer from issues like over-smoothing or over-squashing. To mitigate such issues, existing works typically borrow normalization techniques from training neural networks on Euclidean data or modify the graph structures. Yet these approaches are not well-understood theoretically and could increase the overall computational complexity. In this work, we draw inspirations from spectral graph embedding and propose $\texttt{PowerEmbed}$ -- a simple layer-wise normalization technique to boost MPNNs. We show $\texttt{PowerEmbed}$ can provably express the top-$k$ leading eigenvectors of the graph operator, which prevents over-smoothing and is agnostic to the graph topology; meanwhile, it produces a list of representations ranging from local features to global signals, which avoids over-squashing. We apply $\texttt{PowerEmbed}$ in a wide range of simulated and real graphs and demonstrate its competitive performance, particularly for heterophilous graphs.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes