Stochastic Training of Graph Convolutional Networks with Variance Reduction

By Jianfei Chen, Jun Zhu, Le Song. 2017

566 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Graph Learning

Citations in the corpus

Lifelong Graph Learning (2020, methodology): “oarsened input for the next layer. Ying et al. [40] designed a training strategy that relied on harder-and-harder training examples to improve the robustness and convergence speed of the model. S-GCN [41] developed control variate-based algorithms to sample small neighborhood sizes and used historic”
Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks (2019, methodology): “Also as shown in [2] that VRGCN is faster than FastGCN, so we do not compare with FastGCN here.”
Simple and Deep Graph Convolutional Networks (2020, methodology): “We compare GCNII with the following state-of-the-art methods: GraphSAGE (Hamilton et al., 2017), VR-GCN (Chen et al., 2018b), GaAN (Zhang et al., 2018), GAT (Veliˇckovi´c et al., 2018), JKNet (Xu et al., 2018), GeniePath (Liu et al., 2019), Cluster-GCN (Chiang et al., 2019).”
On the Bottleneck of Graph Neural Networks and its Practical Implications (2020, background): “As observed before (Micheli, 2009; Chen et al., 2018), the receptive ﬁeld of a node in a graph grows exponentially with the number of layers.”
Adaptive Sampling Towards Fast Graph Representation Learning (2018, methodology): “Another related work is the control-variate-based method by [22].”
GNNExplainer: Generating Explanations for Graph Neural Networks (2019, methodology): “Thus, GNNEXPLAINER can be applied to: Graph Convolutional Networks [21], Gated Graph Sequence Neural Networks [26], Jumping Knowledge Networks [36], Attention Networks [33], Graph Networks [4], GNNs with various node aggregation schemes [7, 5, 18, 16, 40, 39, 35], Line-Graph NNs [8], position-aware ”
Graph Transformer Networks (2019, background): “To improve performance or scalability, generalized convolution based on spectral convolution [4, 26], attention mechanism on neighbors [25, 33], subsampling [6, 7] and inductive representation for a large graph [14] have been studied.”
Incremental Training of Graph Neural Networks on Temporal Graphs under Distribution Shift (2020, methodology): “Finally, results from papers on sampling-based graph convolution such as [11,3] can be directly applied to our approach, too, as the sampling can be restricted to the window size given.”
GraphSAINT: Graph Sampling Based Inductive Learning Method (2019, background): “This sampler is inspired by the layer sampler of Chen et al. (2018b).”
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection (2023, methodology): “To counter these challenges, traditional GNN methods utilize sampling strategies like node-wise [304], [305], layer-wise [306], and graph-wise [307] sampling.”