Accelerating Large Scale Real-Time GNN Inference using Channel Pruning

Abstract

Graph Neural Networks (GNNs) are proven to be powerful models to generate node embedding for downstream applications. However, due to the high computation complexity of GNN inference, it is hard to deploy GNNs for large-scale or real-time applications. In this paper, we propose to accelerate GNN inference by pruning the dimensions in each layer with negligible accuracy loss. Our pruning framework uses a novel LASSO regression formulation for GNNs to identify feature dimensions (channels) that have high influence on the output activation. We identify two inference scenarios and design pruning schemes based on their computation and memory usage for each. To further reduce the inference complexity, we effectively store and reuse hidden features of visited nodes, which significantly reduces the number of supporting nodes needed to compute the target embedding. We evaluate the proposed method with the node classification problem on five popular datasets and a real-time spam detection application. We demonstrate that the pruned GNN models greatly reduce computation and memory usage with little accuracy loss. For full inference, the proposed method achieves an average of 3.27x speedup with only 0.002 drop in F1-Micro on GPU. For batched inference, the proposed method achieves an average of 6.67x speedup with only 0.003 drop in F1-Micro on CPU. To the best of our knowledge, we are the first to accelerate large scale real-time GNN inference through channel pruning.

References in corpus (8)

• Semi-Supervised Classification with Graph Convolutional Networks
• Simplifying Graph Convolutional Networks
• Learning Structured Sparsity in Deep Neural Networks
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• A Semi-supervised Graph Attentive Network for Financial Fraud Detection
• Channel Pruning for Accelerating Very Deep Neural Networks
• STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems
• Grale: Designing Networks for Graph Learning

Cited by in corpus (7)

• Trustworthy Graph Neural Networks: Aspects, Methods and Trends
• The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey
• IGB: Addressing The Gaps In Labeling, Features, Heterogeneity, and Size of Public Graph Datasets for Deep Learning Research
• Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning
• View-based Explanations for Graph Neural Networks
• Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving
• A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness