Less Can Be More: Unsupervised Graph Pruning for Large-scale Dynamic Graphs
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.
Code (1)
Tasks
Dynamic Node ClassificationNode ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Segmented Graph-Bert for Graph Instance Modeling
In graph instance representation learning, both the diverse graph instance sizes and the graph node orderless property have been the major obstacles that render existing representation learning models fail to work. In th…
Graph ClassificationRepresentation LearningUnsupervised Atomic Data Mining via Multi-Kernel Graph Autoencoders for Machine Learning Force Fields
Constructing a chemically diverse dataset while avoiding sampling bias is critical to training efficient and generalizable force fields. However, in computational chemistry and materials science, many common dataset gene…
Representation LearningOutlier DetectionAccelerating Deep Unsupervised Domain Adaptation with Transfer Channel Pruning
Deep unsupervised domain adaptation (UDA) has recently received increasing attention from researchers. However, existing methods are computationally intensive due to the computation cost of Convolutional Neural Networks …
Domain AdaptationTransfer LearningUnsupervised Domain AdaptationUncovering Capabilities of Model Pruning in Graph Contrastive Learning
Graph contrastive learning has achieved great success in pre-training graph neural networks without ground-truth labels. Leading graph contrastive learning follows the classical scheme of contrastive learning, forcing mo…
Contrastive LearningGraph ClassificationTransfer LearningEdgePruner: Poisoned Edge Pruning in Graph Contrastive Learning
Graph Contrastive Learning (GCL) is unsupervised graph representation learning that can obtain useful representation of unknown nodes. The node representation can be utilized as features of downstream tasks. However, GCL…
Contrastive LearningGraph Representation LearningNode ClassificationRepresentation Learning