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

by   Jintang Li, et al.

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 edges on a million-scale industrial graph Alipay (7M nodes, 21M edges) while approximating up to 98 https://github.com/EdisonLeeeee/STEP.


page 1

page 2

page 3

page 4


LSP : Acceleration and Regularization of Graph Neural Networks via Locality Sensitive Pruning of Graphs

Graph Neural Networks (GNNs) have emerged as highly successful tools for...

Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods

Many widely used datasets for graph machine learning tasks have generall...

Incremental Training of Graph Neural Networks on Temporal Graphs under Distribution Shift

Current graph neural networks (GNNs) are promising, especially when the ...

Large-scale graph representation learning with very deep GNNs and self-supervision

Effectively and efficiently deploying graph neural networks (GNNs) at sc...

Towards Temporal Edge Regression: A Case Study on Agriculture Trade Between Nations

Recently, Graph Neural Networks (GNNs) have shown promising performance ...

Scalable Adversarial Attack on Graph Neural Networks with Alternating Direction Method of Multipliers

Graph neural networks (GNNs) have achieved high performance in analyzing...

Can Graph Neural Networks Go "Online"? An Analysis of Pretraining and Inference

Large-scale graph data in real-world applications is often not static bu...

Please sign up or login with your details

Forgot password? Click here to reset