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

Zhixian Chen, Tengfei Ma, Zhihua Jin, Yangqiu Song, Yang Wang

Keywords: Graph convolutional networks, graph filtering, Laplacian smooth, ADMM

Abstract: Graph convolutional networks have achieved great success on graph-structured data. Many graph convolutional networks can be regarded as low-pass filters for graph signals. In this paper, we propose a new model, BiGCN, which represents a graph neural network as a bi-directional low-pass filter. Specifically, we not only consider the original graph structure information but also the latent correlation between features, thus BiGCN can filter the signals along with both the original graph and a latent feature-connection graph. Our model outperforms previous graph neural networks in the tasks of node classification and link prediction on benchmark datasets, especially when we add noise to the node features.

One-sentence Summary: We propose BiGCN, which utilizes additional information from a latent feature graph and represents a graph neural network as a bi-directional low-pass filter.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2101.05519/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=gh-PjgXNV