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.

本文介绍了一种二进制图卷积神经网络（Bi-GCN），它将网络参数和输入节点特征进行二元化，并将原始矩阵乘法改为二进制运算以加速计算，并使用一种新的梯度逼近反向传播方法来训练我们的Bi-GCN。实验表明，与全精度基线相比，Bi-GCN在节省内存资源方面平均可以减少约30倍，并平均加速推理速度约47倍，并且该二进制方法还可以轻松应用于其他GNNs。

Bi-GCN: 二元图卷积网络