Inference-friendly Graph Compression for Graph Neural Networks
Summary: IFGC uses an inference-equivalence relation to compress G into a compact G_c that preserves GNN-indistinguishable node pairs, enabling direct or low-overhead inference to accelerate GNNs on large graphs. Three variants—SPGC (direct), (α,r)-compression (tradeoff), and anchored (node-focused)—with provable algorithms and empirical validation. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yangxin Fan
- 2. Haolai Che
- 3. Yinghui Wu
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 |
|---|---|---|---|---|
| 2,177 | Accelerating Large Scale Real-Time GNN Inference using Channel Pruning | 2021 | VLDB | 9.359876e-05 |
| 5,994 | A Query Language Perspective on Graph Learning | 2023 | PODS | 5.2415551e-05 |
| 13,181 | Spatio-Temporal Denoising Graph Autoencoders with Data Augmentation for Photovoltaic Data Imputation | 2023 | SIGMOD | - |
Previous
Page 1 / 1
Next