Measuring and Sampling: A Metric-guided Subgraph Learning Framework for Graph Neural Network
Not on the map. Why?
Abstract (arXiv)
Graph neural network (GNN) has shown convincing performance in learning powerful node representations that preserve both node attributes and graph structural information. However, many GNNs encounter problems in effectiveness and efficiency when they are designed with a deeper network structure or handle large-sized graphs. Several sampling algorithms have been proposed for improving and accelerating the training of GNNs, yet they ignore understanding the source of GNN performance gain. The measurement of information within graph data can help the sampling algorithms to keep high-value information while removing redundant information and even noise. In this paper, we propose a Metric-Guided (MeGuide) subgraph learning framework for GNNs. MeGuide employs two novel metrics: Feature Smoothness and Connection Failure Distance to guide the subgraph sampling and mini-batch based training. Feature Smoothness is designed for analyzing the feature of nodes in order to retain the most valuable information, while Connection Failure Distance can measure the structural information to control the size of subgraphs. We demonstrate the effectiveness and efficiency of MeGuide in training various GNNs on multiple datasets.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 35 of its 45 references that are in the map. First posted on arXiv 30 Dec 2021.
Builds on
35 of 45 references.
References · 35
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
- 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
- 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
- 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
- 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
23 more
- 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
- 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
- 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
- 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
- 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
- 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
- 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
- 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
- 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
- 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
- 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
- 2019Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networkscited by 177
- 2018Adaptive Graph Convolutional Neural Networkscited by 155
- 2018Large-Scale Learnable Graph Convolutional Networkscited by 113
- 2020Scalable Graph Neural Networks via Bidirectional Propagationcited by 87
- 2019LanczosNet: Multi-Scale Deep Graph Convolutional Networkscited by 73
- 2020Tackling Over-Smoothing for General Graph Convolutional Networkscited by 66
- 2019GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animationcited by 21
- 2020Ripple Walk Training: A Subgraph-based training framework for Large and Deep Graph Neural Networkcited by 19
- 2019Graph Star Net for Generalized Multi-Task Learningcited by 11
- 2021Label Contrastive Coding based Graph Neural Network for Graph Classificationcited by 10
- 2020Fake News Detection on News-Oriented Heterogeneous Information Networks through Hierarchical Graph Attentioncited by 6
- 2018Social Network Fusion and Mining: A Surveycited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.