LGSIMay 19, 2022

A Simple Yet Effective SVD-GCN for Directed Graphs

arXiv:2205.09335v110 citationsh-index: 26
Originality Incremental advance
AI Analysis

This is an incremental improvement for graph neural networks applied to directed graphs.

The authors tackled the problem of node classification on directed graphs by proposing SVD-GCN, a graph neural network based on Singular Value Decomposition, which outperformed GCN and other state-of-the-art methods on several datasets.

In this paper, we propose a simple yet effective graph neural network for directed graphs (digraph) based on the classic Singular Value Decomposition (SVD), named SVD-GCN. The new graph neural network is built upon the graph SVD-framelet to better decompose graph signals on the SVD ``frequency'' bands. Further the new framelet SVD-GCN is also scaled up for larger scale graphs via using Chebyshev polynomial approximation. Through empirical experiments conducted on several node classification datasets, we have found that SVD-GCN has remarkable improvements in a variety of graph node learning tasks and it outperforms GCN and many other state-of-the-art graph neural networks for digraphs. Moreover, we empirically demonstate that the SVD-GCN has great denoising capability and robustness to high level graph data attacks. The theoretical and experimental results prove that the SVD-GCN is effective on a variant of graph datasets, meanwhile maintaining stable and even better performance than the state-of-the-arts.

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