When Does A Spectral Graph Neural Network Fail in Node Classification?

no code implementations • 16 Feb 2022 • Zhixian Chen, Tengfei Ma, Yang Wang

Although graph filters provide theoretical foundations for model explanations, it is unclear when a spectral GNN will fail.

Graph Learning Node Classification

Graph Information Matters: Understanding Graph Filters from Interaction Probability

no code implementations • 29 Sep 2021 • Zhixian Chen, Tengfei Ma, Yang Wang

We show that the homophily degree of graphs significantly affects the prediction error of graph filters.

Graph Learning Node Classification

Wasserstein Graph Neural Networks for Graphs with Missing Attributes

no code implementations • 6 Feb 2021 • Zhixian Chen, Tengfei Ma, Yangqiu Song, Yang Wang

In this paper, we propose an innovative node representation learning framework, Wasserstein Graph Neural Network (WGNN), to mitigate the problem.

Attribute Graph Representation Learning +3

BiGCN: A Bi-directional Low-Pass Filtering Graph Neural Network

no code implementations • 14 Jan 2021 • Zhixian Chen, Tengfei Ma, Zhihua Jin, Yangqiu Song, Yang Wang

Graph convolutional networks (GCNs) have achieved great success on graph-structured data.

Denoising Link Prediction +1