FastGCN swMATH ID: 38089 Software Authors: Jie Chen, Tengfei Ma, Cao Xiao Description: FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling. The graph convolutional networks (GCN) recently proposed by Kipf and Welling are an effective graph model for semi-supervised learning. This model, however, was originally designed to be learned with the presence of both training and test data. Moreover, the recursive neighborhood expansion across layers poses time and memory challenges for training with large, dense graphs. To relax the requirement of simultaneous availability of test data, we interpret graph convolutions as integral transforms of embedding functions under probability measures. Such an interpretation allows for the use of Monte Carlo approaches to consistently estimate the integrals, which in turn leads to a batched training scheme as we propose in this work—FastGCN. Enhanced with importance sampling, FastGCN not only is efficient for training but also generalizes well for inference. We show a comprehensive set of experiments to demonstrate its effectiveness compared with GCN and related models. In particular, training is orders of magnitude more efficient while predictions remain comparably accurate. Homepage: https://arxiv.org/abs/1801.10247 Source Code: https://github.com/matenure/FastGCN Related Software: PyTorch; DeepWalk; Adam; node2vec; AFGen; Graclus; BRENDA; struc2vec; GraphRNN; MolGAN; Tensor2Tensor; NetKit; kLog; MoleculeNet; UCI-ml; GitHub; IMPALA; darch; DGL; DeepGCNs Cited in: 8 Publications all top 5 Cited by 29 Authors 3 Li, Ming 2 Ma, Zheng 2 Wang, Yuguang 1 Alfke, Dominik 1 Bacciu, Davide 1 Cao, Feilong 1 Chen, Bing 1 Errica, Federico 1 Friel, Nial 1 Li, Jundong 1 Liang, Jianqing 1 Liang, Jiye 1 Liò, Pietro 1 Luo, Minnan 1 Micheli, Alessio 1 Pham, Thuan Q. 1 Podda, Marco 1 Stoll, Martin 1 Suya, Fnu 1 Tan, Leonard 1 Tan, Linda S. L. 1 Tao, Xiaohui 1 Wang, Jihong 1 Xuan, Junyu 1 Yang, Zijiang 1 Yao, Kaixuan 1 Zhang, Ji 1 Zheng, Qinghua 1 Zhuang, Xiaosheng all top 5 Cited in 6 Serials 2 Neural Networks 2 Data Mining and Knowledge Discovery 1 Artificial Intelligence 1 Journal of Statistical Mechanics: Theory and Experiment 1 Journal of Computational and Graphical Statistics 1 Computer Science Review all top 5 Cited in 6 Fields 6 Computer science (68-XX) 2 Combinatorics (05-XX) 1 Statistics (62-XX) 1 Statistical mechanics, structure of matter (82-XX) 1 Game theory, economics, finance, and other social and behavioral sciences (91-XX) 1 Information and communication theory, circuits (94-XX) Citations by Year