CompressGNN: Accelerating Graph Neural Network Training via Hierarchical Compression
Open Access
- 3 August 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 286-297
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62322213, 62461146205)
- Beijing Nova Program (20230484397, 20220484137)
This publication has 52 references indexed in Scilit:
- Breaking the Edge: Enabling Efficient Neural Network Inference on Integrated Edge DevicesIEEE Transactions on Cloud Computing, 2025
- POCLib: A High-Performance Framework for Enabling Near Orthogonal Processing on CompressionIEEE Transactions on Parallel and Distributed Systems, 2021
- ALG: Fast and Accurate Active Learning Framework for Graph Convolutional Networks2021
- Training Robust Neural Networks Using Lipschitz BoundsIEEE Control Systems Letters, 2021
- DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs2020
- FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems2020
- TADOC: Text analytics directly on compressionThe VLDB Journal, 2020
- Graph Convolutional Neural Networks for Web-Scale Recommender Systems2018
- A scalable pattern mining approach to web graph compression with communities2008
- Approximate nearest neighbors1998