Learning Steady-States of Iterative Algorithms over Graphs

By Hanjun Dai, Zornitsa Kozareva, Bo Dai, Alex Smola, Le Song. 2018

222 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.

Citations in the corpus

Predict then Propagate: Graph Neural Networks meet Personalized PageRank (2018, background): “…message passing (or neighbor aggregation) algorithms (Kearnes et al., 2016; Kipf & Welling, 2017; Hamilton et al., 2017; Pham et al., 2017; Monti et al., 2017; Gilmer et al., 2017), and neighbor aggregation via recurrent neural networks (Scarselli et al., 2009; Li et al., 2016; Dai et al., 2018).”
Graph convolutional networks: a comprehensive review (2019, background): “) , node u, SSE first samples a set of nodes Ṽ from V and updates the node representations for T iterations to be close to stability by: where node u ∈ Ṽ and T is the aggregation function defined by: where X0(u,”
Graph Neural Networks: A Review of Methods and Applications (2018, methodology): “Following reinforcement learning, SSE [80] proposed Stochastic Fixed-Point Gradient Descent for GNN training.”
Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, background): “There is a large literature on the design of the transform function (see, e.g., [140, 123, 87, 51]).”
Representation Learning for Dynamic Graphs: A Survey (2019, methodology): “(2018) uses this approach where M is the GCN proposed by Defferrard et al. (2016) and the RNN is a standard LSTM.”
AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing (2019, background): “In the past decade, work has continued on optimizing GNN algorithms exploring new neural network approaches [8], [19], [20], [22]–[25].”
Graph Learning: A Survey (2021, methodology): “[138] proposed the SSE algorithm, which uses asynchronous random to learn vertex representation so as to improve learning efficiency.”
NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification (2023, background): “heterophily [53], over-squashing [2], long-range dependencies [8], and graph incompleteness [11], etc.”
Multi-Stage Self-Supervised Learning for Graph Convolutional Networks (2019, background): “…of graph-structured data and it has been demonstrated that GCNs and their variants (Hamilton, Ying, and Leskovec 2017; Velickovic et al. 2017; Dai et al. 2018; Chen and Zhu 2017) signiﬁcantly outperform traditional multi-layer perceptron (MLP) models and traditional graph embedding…”
Implicit Graph Neural Networks (2020, methodology): “SGC (Wu et al., 2019a) GCN (Kipf and Welling, 2016) struct2vec (Dai et al., 2016) SSE (Dai et al., 2018) IGNN To further manifest the scalability of IGNN towards larger graphs, we conduct experiments on a large multi-label node classiﬁcation data set, namely the Amazon product co-purchasing network…”
Deep Learning on Graphs: A Survey (2018, unknown): “However, instead of using a GRU in the calculation, SSE adopted stochastic ﬁxed-point gradient descent to accelerate the training process.”
Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs (2019, methodology): “There are also many methods for graph embedding, e.g., structure2vec (Dai et al., 2016), SSE (Dai et al., 2018), and JK-Net(Xu et al., 2018).”
HyGCN: A GCN Accelerator with Hybrid Architecture (2020, background): “solve problems including node classification [12], link prediction [9, 13], graph clustering [10], and recommendation [14].”