# Less Can Be More: Unsupervised Graph Pruning for Large-scale Dynamic Graphs

arXiv: https://arxiv.org/abs/2305.10673 · HTML: https://mlsanity.com/paper/2305.10673/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 38 references that are in the map.
- First posted on arXiv 18 May 2023.

## Builds on (most cited first, 30 of 32)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks](https://mlsanity.com/paper/2004.05937/) (2020)
- [Graph Self-Supervised Learning: A Survey](https://mlsanity.com/paper/2103.00111/) (2021)
- [Representation Learning for Dynamic Graphs: A Survey](https://mlsanity.com/paper/1905.11485/) (2019)
- [Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation](https://mlsanity.com/paper/2110.08727/) (2021)
- [Learning to Drop: Robust Graph Neural Network via Topological Denoising](https://mlsanity.com/paper/2011.07057/) (2020)
- [A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability](https://mlsanity.com/paper/2204.08570/) (2022)
- [InfoGCL: Information-Aware Graph Contrastive Learning](https://mlsanity.com/paper/2110.15438/) (2021)
- [Retrosynthesis Prediction with Conditional Graph Logic Network](https://mlsanity.com/paper/2001.01408/) (2020)
- [NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs](https://mlsanity.com/paper/2106.04714/) (2021)
- [Contrastive Self-supervised Learning for Graph Classification](https://mlsanity.com/paper/2009.05923/) (2020)
- [Node Embedding over Temporal Graphs](https://mlsanity.com/paper/1903.08889/) (2019)
- [A Survey of Adversarial Learning on Graphs](https://mlsanity.com/paper/2003.05730/) (2020)
- [Accelerating Large Scale Real-Time GNN Inference using Channel Pruning](https://mlsanity.com/paper/2105.04528/) (2021)
- [Understanding Structural Vulnerability in Graph Convolutional Networks](https://mlsanity.com/paper/2108.06280/) (2021)
- [Second-Order Pooling for Graph Neural Networks](https://mlsanity.com/paper/2007.10467/) (2020)

## Built on by (most cited first, 7 of 7)

- [A survey of dynamic graph neural networks](https://mlsanity.com/paper/2404.18211/) (2024)
- [State Space Models on Temporal Graphs: A First-Principles Study](https://mlsanity.com/paper/2406.00943/) (2024)
- [A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks](https://mlsanity.com/paper/2305.19306/) (2023)
- [Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligence](https://mlsanity.com/paper/2407.15320/) (2024)
- [TASER: Temporal Adaptive Sampling for Fast and Accurate Dynamic Graph Representation Learning](https://mlsanity.com/paper/2402.05396/) (2024)
- [FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Sampling](https://mlsanity.com/paper/2501.12592/) (2025)
- [LasTGL: An Industrial Framework for Large-Scale Temporal Graph Learning](https://mlsanity.com/paper/2311.16605/) (2023)

## Abstract (arXiv)

The prevalence of large-scale graphs poses great challenges in time and storage for training and deploying graph neural networks (GNNs). Several recent works have explored solutions for pruning the large original graph into a small and highly-informative one, such that training and inference on the pruned and large graphs have comparable performance. Although empirically effective, current researches focus on static or non-temporal graphs, which are not directly applicable to dynamic scenarios. In addition, they require labels as ground truth to learn the informative structure, limiting their applicability to new problem domains where labels are hard to obtain. To solve the dilemma, we propose and study the problem of unsupervised graph pruning on dynamic graphs. We approach the problem by our proposed STEP, a self-supervised temporal pruning framework that learns to remove potentially redundant edges from input dynamic graphs. From a technical and industrial viewpoint, our method overcomes the trade-offs between the performance and the time & memory overheads. Our results on three real-world datasets demonstrate the advantages on improving the efficacy, robustness, and efficiency of GNNs on dynamic node classification tasks. Most notably, STEP is able to prune more than 50% of edges on a million-scale industrial graph Alipay (7M nodes, 21M edges) while approximating up to 98% of the original performance. Code is available at https://github.com/EdisonLeeeee/STEP.