GNN Transformation Framework for Improving Efficiency and Scalability
Not on the map. Why?
Abstract (arXiv)
We propose a framework that automatically transforms non-scalable GNNs into precomputation-based GNNs which are efficient and scalable for large-scale graphs. The advantages of our framework are two-fold; 1) it transforms various non-scalable GNNs to scale well to large-scale graphs by separating local feature aggregation from weight learning in their graph convolution, 2) it efficiently executes precomputation on GPU for large-scale graphs by decomposing their edges into small disjoint and balanced sets. Through extensive experiments with large-scale graphs, we demonstrate that the transformed GNNs run faster in training time than existing GNNs while achieving competitive accuracy to the state-of-the-art GNNs. Consequently, our transformation framework provides simple and efficient baselines for future research on scalable GNNs.
Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 22 of its 34 references that are in the map. First posted on arXiv 25 Jul 2022.
Builds on
22 of 34 references.
References · 22
- 2014Adam: A Method for Stochastic Optimizationcited by 37,093
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
- 2017Graph Attention Networkscited by 8,888
- 2017Inductive Representation Learning on Large Graphscited by 6,303
- 2018How Powerful are Graph Neural Networks?cited by 4,373
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,911
- 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,472
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,157
- 2019Simplifying Graph Convolutional Networkscited by 1,474
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 991
- 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
- 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
10 more
- 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
- 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
- 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 541
- 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
- 2018Deep Learning on Graphs: A Surveycited by 393
- 2020SIGN: Scalable Inception Graph Neural Networkscited by 284
- 2020DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphscited by 139
- 2021Improving Graph Neural Networks with Simple Architecture Designcited by 41
- 2020Deep Graph Neural Networks with Shallow Subgraph Samplerscited by 16
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.