Inference-friendly Graph Compression for Graph Neural Networks
Summary: Introduces inference-friendly graph compression, defining GNN-specific inference equivalence to merge indistinguishable nodes. SPGC, configurable (α,r)-compression, and anchored compression enable direct or low-cost inference with quality/efficiency guarantees. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yangxin Fan (Case Western Reserve University)
- 2. Haolai Che (Case Western Reserve University)
- 3. Yinghui Wu (Case Western Reserve University)
BibTeX Citation
@article{fan_vldb25,
title = {{Inference-friendly Graph Compression for Graph Neural Networks}},
author = {Fan, Yangxin and Che, Haolai and Wu, Yinghui},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {9},
pages = {3203--3215},
doi = {10.14778/3746405.3746438},
url = {https://doi.org/10.14778/3746405.3746438},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2,386 | Accelerating Large Scale Real-Time GNN Inference using Channel Pruning | 2021 | VLDB | 8.6490185e-05 |
| 5,893 | A Query Language Perspective on Graph Learning | 2023 | PODS | 6.0486927e-05 |
| 13,384 | Spatio-Temporal Denoising Graph Autoencoders with Data Augmentation for Photovoltaic Data Imputation | 2023 | SIGMOD | - |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,190 | Topology-preserving Graph Coarsening: An Elementary Collapse-based Approach | 2024 | VLDB |
| 2 | 11,236 | Improving Graph Compression for Efficient Resource-Constrained Graph Analytics | 2024 | VLDB |
| 3 | 8,187 | Demystifying Graph Sparsification Algorithms in Graph Properties Preservation | 2024 | VLDB |
| 4 | 10,450 | Enabling Efficient Direct Update on Rule-Based Compressed Graph | 2026 | SIGMOD |
| 5 | 1,336 | Query Preserving Graph Compression | 2012 | SIGMOD |
| 6 | 2,386 | Accelerating Large Scale Real-Time GNN Inference using Channel Pruning | 2021 | VLDB |
| 7 | 6,630 | Efficient Training of Graph Neural Networks on Large Graphs | 2024 | VLDB |
| 8 | 6,408 | CompressGraph: Efficient Parallel Graph Analytics with Rule-Based Compression | 2023 | SIGMOD |
| 9 | 6,652 | Eliminating Data Processing Bottlenecks in GNN Training over Large Graphs via Two-level Feature Compression | 2024 | VLDB |
| 10 | 11,021 | Graph Compression for Interpretable Graph Neural Network Inference At Scale | 2025 | VLDB |