mlsanityData to 14 Oct 2026

Inference-friendly Graph Compression for Graph Neural Networks

arXiv 2504.13034 ↗First posted 17 Apr 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have demonstrated promising performance in graph analysis. Nevertheless, the inference process of GNNs remains costly, hindering their applications for large graphs. This paper proposes inference-friendly graph compression (IFGC), a graph compression scheme to accelerate GNNs inference. Given a graph G and a GNN M, an IFGC computes a small compressed graph Gc, to best preserve the inference results of M over G, such that the result can be directly inferred by accessing Gc with no or little decompression cost. (1) We characterize IFGC with a class of inference equivalence relation. The relation captures the node pairs in G that are not distinguishable for GNN inference. (2) We introduce three practical specifications of IFGC for representative GNNs: structural preserving compression (SPGC), which computes Gc that can be directly processed by GNN inference without decompression; (α, r)-compression, that allows for a configurable trade-off between compression ratio and inference quality, and anchored compression that preserves inference results for specific nodes of interest. For each scheme, we introduce compression and inference algorithms with guarantees of efficiency and quality of the inferred results. We conduct extensive experiments on diverse sets of large-scale graphs, which verifies the effectiveness and efficiency of our graph compression approaches.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 62 references that are in the map. First posted on arXiv 17 Apr 2025.

Builds on

30 of 62 references.

References · 30

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  7. 2018Link Prediction Based on Graph Neural Networkscited by 832
  8. 2019Graph Neural Networks for Social Recommendationcited by 714
  9. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  10. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  11. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 329
  12. 2022Graph neural networks for materials science and chemistrycited by 182
18 more
  1. 2021A Unified Lottery Ticket Hypothesis for Graph Neural Networkscited by 118
  2. 2020Expressive Power of Invariant and Equivariant Graph Neural Networkscited by 100
  3. 2020Degree-Quant: Quantization-Aware Training for Graph Neural Networkscited by 96
  4. 2023Everything is Connected: Graph Neural Networkscited by 85
  5. 2021Scaling Up Graph Neural Networks Via Graph Coarseningcited by 80
  6. 2024A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensationcited by 57
  7. 2018Spectrally approximating large graphs with smaller graphscited by 56
  8. 2021Adaptive Transfer Learning on Graph Neural Networkscited by 31
  9. 2022Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysiscited by 29
  10. 2022Survey on Graph Neural Network Acceleration: An Algorithmic Perspectivecited by 26
  11. 2016Small-World Brain Networks Revisitedcited by 16
  12. 2023Search to Fine-tune Pre-trained Graph Neural Networks for Graph-level Taskscited by 13
  13. 2018Survey and Taxonomy of Lossless Graph Compression and Space-Efficient Graph Representationscited by 12
  14. 2022Efficient Graph Neural Network Inference at Large Scalecited by 7
  15. 2024Graph-Skeleton: ~1% Nodes are Sufficient to Represent Billion-Scale Graphcited by 6
  16. 2020Automorphic Equivalence-aware Graph Neural Networkcited by 5
  17. 2022Detecting Anomalous Cryptocurrency Transactions: an AML/CFT Application of Machine Learning-based Forensicscited by 5
  18. 2023Learning Graph Neural Networks using Exact Compressioncited by 3

Built on by

Not cited yet.