arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.11147cs.LGstat.ML
收藏

二值化图神经网络

Binarized Graph Neural Network

CAI, University of Technology, Sydney(悉尼科技大学CAI);University of Science and Technology of China(中国科学技术大学);University of Technology, Sydney(悉尼科技大学);University of New South Wales(新南威尔士大学)

Hanchen Wang, Defu Lian, Ying Zhang, Lu Qin, Xiangjian He, Yiguang Lin, Xuemin Lin

摘要:

最近,通过应用遵循邻域聚合方案的图神经网络(GNNs),在图分析中已经有了一些突破,其在许多任务中表现出出色的性能。然而,我们观察到,在现有的基于GNN的图嵌入方法中,网络的参数和节点的嵌入是用实值矩阵表示的,这可能会限制这些模型的效率和可扩展性。众所周知,二进制向量通常比实值向量具有更高的空间和时间效率。这促使我们开发一个二进制化的图神经网络,学习二进制网络参数的节点的二进制表示遵循基于GNN的范式。我们提出的方法可以无缝集成到现有的基于GNN的嵌入方法中,以二进制化模型参数并学习紧凑嵌入。大量的实验表明,所提出的二值化图神经网络,即BGN,是数量级更有效的时间和空间方面,同时匹配的最先进的性能。

英文摘要:

Recently, there have been some breakthroughs in graph analysis by applying the graph neural networks (GNNs) following a neighborhood aggregation scheme, which demonstrate outstanding performance in many tasks. However, we observe that the parameters of the network and the embedding of nodes are represented in real-valued matrices in existing GNN-based graph embedding approaches which may limit the efficiency and scalability of these models. It is well-known that binary vector is usually much more space and time efficient than the real-valued vector. This motivates us to develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters following the GNN-based paradigm. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches to binarize the model parameters and learn the compact embedding. Extensive experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space while matching the state-of-the-art performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑