DBScholar

Back to papers

Accelerating Large Scale Real-Time GNN Inference using Channel Pruning

Summary: Channel pruning via LASSO identifies influential GNN channels per layer for large-scale real-time inference. Two inference regimes and a feature-reuse scheme cut compute/memory, achieving 3.27x GPU and 6.67x CPU speedups with minimal accuracy loss. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
hc152e2e27e2c5453
Venue
VLDB
Year
2021
Pagerank
8.4652234e-05
Overall Rank
2,439 | 83.61%
DOI
10.14778/3461535.3461547

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{zhou_vldb21,
        title = {{Accelerating Large Scale Real-Time GNN Inference using Channel Pruning}},
        author = {Zhou, Hongkuan and Srivastava, Ajitesh and Zeng, Hanqing and Kannan, Rajgopal and Prasanna, Viktor},
        journal = {PVLDB},
        series = {{VLDB} '21},
        volume = {14},
        number = {9},
        pages = {1597--1605},
        doi = {10.14778/3461535.3461547},
        url = {https://doi.org/10.14778/3461535.3461547},
        year = {2021}
}

Incoming Citations (Sorted by Pagerank)

Showing 11 of 11 citing papers.

Rank Citing Paper Year Venue Pagerank
1,134 SANCUS: Staleness-Aware Communication-Avoiding Full-Graph Decentralized Training in Large-Scale Graph Neural Networks 2022 VLDB 0.00011893521
4,622 Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning 2022 VLDB 6.4982876e-05
6,166 Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving 2025 SIGMOD 5.8631131e-05
9,900 Scalable Graph Convolutional Network Training on Distributed-Memory Systems 2023 VLDB 5.1116429e-05
10,105 View-based Explanations for Graph Neural Networks 2024 SIGMOD 5.0789354e-05
10,520 A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness 2026 SIGMOD 4.9793485e-05
10,609 SG-Serve: Efficient Model Serving for Subgraph-based Graph Representation Learning 2026 SIGMOD 4.9793485e-05
10,706 Efficient GNN Training on Giant Graphs with Collective Batching and Scheduling 2026 VLDB 4.9793485e-05
11,307 Inference-friendly Graph Compression for Graph Neural Networks 2025 VLDB 4.9793485e-05
11,386 Graph Compression for Interpretable Graph Neural Network Inference At Scale 2025 VLDB 4.9793485e-05
11,609 Complex-Path: Effective and Efficient Node Ranking with Paths in Billion-Scale Heterogeneous Graphs 2024 VLDB 4.9793485e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 0 of 0 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 4,826 Accelerating Sampling and Aggregation Operations in GNN Frameworks with GPU Initiated Direct Storage Accesses 2024 VLDB
2 4,898 Comprehensive Evaluation of GNN Training Systems: A Data Management Perspective 2024 VLDB
3 1,772 ByteGNN: Efficient Graph Neural Network Training at Large Scale 2022 VLDB
4 6,826 SIMPLE: Efficient Temporal Graph Neural Network Training at Scale with Dynamic Data Placement 2024 SIGMOD
5 6,780 Eliminating Data Processing Bottlenecks in GNN Training over Large Graphs via Two-level Feature Compression 2024 VLDB
6 10,520 A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness 2026 SIGMOD
7 5,339 FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training 2024 VLDB
8 6,669 Efficient Training of Graph Neural Networks on Large Graphs 2024 VLDB
9 11,307 Inference-friendly Graph Compression for Graph Neural Networks 2025 VLDB
10 2,596 Scalable and Efficient Full-Graph GNN Training for Large Graphs 2023 SIGMOD