# Ripple Walk Training: A Subgraph-based training framework for Large and Deep Graph Neural Network

arXiv: https://arxiv.org/abs/2002.07206 · HTML: https://mlsanity.com/paper/2002.07206/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2020.

## Built on by (most cited first, 19 of 19)

- [Sampling methods for efficient training of graph convolutional networks: A survey](https://mlsanity.com/paper/2103.05872/) (2021)
- [Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks](https://mlsanity.com/paper/2207.08629/) (2022)
- [A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware](https://mlsanity.com/paper/2306.14052/) (2023)
- [A Comprehensive Survey on Distributed Training of Graph Neural Networks](https://mlsanity.com/paper/2211.05368/) (2022)
- [Scalable Graph Neural Network Training: The Case for Sampling](https://mlsanity.com/paper/2105.02315/) (2021)
- [Learning on Large Graphs using Intersecting Communities](https://mlsanity.com/paper/2405.20724/) (2024)
- [Two-level Graph Neural Network](https://mlsanity.com/paper/2201.01190/) (2022)
- [FunQG: Molecular Representation Learning Via Quotient Graphs](https://mlsanity.com/paper/2207.08597/) (2022)
- [Modeling Multi-Destination Trips with Sketch-Based Model](https://mlsanity.com/paper/2102.11252/) (2021)
- [Measuring and Sampling: A Metric-guided Subgraph Learning Framework for Graph Neural Network](https://mlsanity.com/paper/2112.15015/) (2021)
- [Rethinking Efficiency and Redundancy in Training Large-scale Graphs](https://mlsanity.com/paper/2209.00800/) (2022)
- [T-EMDE: Sketching-based global similarity for cross-modal retrieval](https://mlsanity.com/paper/2105.04242/) (2021)
- [PolicyClusterGCN: Identifying Efficient Clusters for Training Graph Convolutional Networks](https://mlsanity.com/paper/2306.14357/) (2023)
- [Graph Convolutional Network For Semi-supervised Node Classification With Subgraph Sketching](https://mlsanity.com/paper/2404.12724/) (2024)
- [Acceleration Algorithms in GNNs: A Survey](https://mlsanity.com/paper/2405.04114/) (2024)
- [Hierarchical graph sampling based minibatch learning with chain preservation and variance reduction](https://mlsanity.com/paper/2503.00860/) (2025)
- [Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training](https://mlsanity.com/paper/2604.02651/) (2026)
- [Empowering Credit Risk Detection in Weixin Pay with Billion-Scale Deep Graph Learning](https://mlsanity.com/paper/2608.02168/) (2026)
- [LGNNIC: Acceleration of Large-Scale GNN Training using SmartNICs](https://mlsanity.com/paper/2608.07733/) (2026)

## Abstract (arXiv)

Graph neural networks (GNNs) have achieved outstanding performance in learning graph-structured data and various tasks. However, many current GNNs suffer from three common problems when facing large-size graphs or using a deeper structure: neighbors explosion, node dependence, and oversmoothing. Such problems attribute to the data structures of the graph itself or the designing of the multi-layers GNNs framework, and can lead to low training efficiency and high space complexity. To deal with these problems, in this paper, we propose a general subgraph-based training framework, namely Ripple Walk Training (RWT), for deep and large graph neural networks. RWT samples subgraphs from the full graph to constitute a mini-batch, and the full GNN is updated based on the mini-batch gradient. We analyze the high-quality subgraphs to train GNNs in a theoretical way. A novel sampling method Ripple Walk Sampler works for sampling these high-quality subgraphs to constitute the mini-batch, which considers both the randomness and connectivity of the graph-structured data. Extensive experiments on different sizes of graphs demonstrate the effectiveness and efficiency of RWT in training various GNNs (GCN & GAT).