Bi-GCN: Binary Graph Convolutional Network

by   Junfu Wang, et al.

Graph Neural Networks (GNNs) have achieved tremendous success in graph representation learning. Unfortunately, current GNNs usually rely on loading the entire attributed graph into the network for processing. This implicit assumption may not be satisfied with limited memory resources, especially when the attributed graph is large. In this paper, we propose a Binary Graph Convolutional Network (Bi-GCN), which binarizes both the network parameters and input node features. Besides, the original matrix multiplications are revised to binary operations for accelerations. According to the theoretical analysis, our Bi-GCN can reduce the memory consumption by  31x for both the network parameters and input data, and accelerate the inference speed by  53x. Extensive experiments have demonstrated that our Bi-GCN can give a comparable prediction performance compared to the full-precision baselines. Besides, our binarization approach can be easily applied to other GNNs, which has been verified in the experiments.



page 1

page 2

page 3

page 4


Label-GCN: An Effective Method for Adding Label Propagation to Graph Convolutional Networks

We show that a modification of the first layer of a Graph Convolutional ...

H-GCN: A Graph Convolutional Network Accelerator on Versal ACAP Architecture

Graph Neural Networks (GNNs) have drawn tremendous attention due to thei...

Inferring Multiple Relationships between ASes using Graph Convolutional Network

Precisely understanding the business relationships between Autonomous Sy...

Explainable, Stable, and Scalable Graph Convolutional Networks for Learning Graph Representation

The network embedding problem that maps nodes in a graph to vectors in E...

An Anatomy of Graph Neural Networks Going Deep via the Lens of Mutual Information: Exponential Decay vs. Full Preservation

Graph Convolutional Network (GCN) has attracted intensive interests rece...

CPR-GCN: Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary Arteries

Automated anatomical labeling plays a vital role in coronary artery dise...

Benchmark Tests of Convolutional Neural Network and Graph Convolutional Network on HorovodRunner Enabled Spark Clusters

The freedom of fast iterations of distributed deep learning tasks is cru...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.