mlsanityData to 7 Oct 2026

Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN Pipelines

arXiv 2603.06952 ↗First posted 7 Mar 2026cs.LG cs.DBcited by 0

Not on the map. Why?

Abstract (arXiv)

As graphs scale to billions of nodes and edges, graph Machine Learning workloads are constrained by the cost of multi-hop traversals over exponentially growing neighborhoods. While various system-level and algorithmic optimizations have been proposed to accelerate Graph Neural Network (GNN) pipelines, data management and movement remain the primary bottlenecks at scale. In this paper, we explore whether graph sparsification, a well-established technique that reduces edges to create sparser neighborhoods, can serve as a lightweight pre-processing step to address these bottlenecks while preserving accuracy on node classification tasks. We develop an extensible experimental framework that enables systematic evaluation of how different sparsification methods affect the performance and accuracy of GNN models. We conduct the first comprehensive study of GNN training and inference on sparsified graphs, revealing several key findings. First, sparsification often preserves or even improves predictive performance. As an example, random sparsification raises the accuracy of the GAT model by 6.8% on the PubMed graph. Second, benefits increase with scale, substantially accelerating both training and inference. Our results show that the K-Neighbor sparsifier improves model serving performance on the Products graph by 11.7x with only a 0.7% accuracy drop. Importantly, we find that the computational overhead of sparsification is quickly amortized, making it practical for very large graphs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 62 references that are in the map. First posted on arXiv 7 Mar 2026.

Builds on

26 of 62 references.

References · 26

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  5. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  6. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  7. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  8. 2020DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphscited by 139
  9. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  10. 2021Scaling Up Graph Neural Networks Via Graph Coarseningcited by 80
  11. 2021BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessingcited by 50
  12. 2025PyG 2.0: Scalable Learning on Real World Graphscited by 49
14 more
  1. 2024Macro Graph Neural Networks for Online Billion-Scale Recommender Systemscited by 40
  2. 2021Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipeliningcited by 39
  3. 2021Distributed Hybrid CPU and GPU training for Graph Neural Networks on Billion-Scale Graphscited by 33
  4. 2022Ginex: SSD-enabled Billion-scale Graph Neural Network Training on a Single Machine via Provably Optimal In-memory Cachingcited by 21
  5. 2021Sequential Aggregation and Rematerialization: Distributed Full-batch Training of Graph Neural Networks on Large Graphscited by 18
  6. 2023A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardwarecited by 18
  7. 2023Demystifying Graph Sparsification Algorithms in Graph Properties Preservationcited by 14
  8. 2016Structure-Preserving Sparsification Methods for Social Networkscited by 10
  9. 2024Graph Neural Network Training Systems: A Performance Comparison of Full-Graph and Mini-Batchcited by 10
  10. 2023Comprehensive Evaluation of GNN Training Systems: A Data Management Perspectivecited by 9
  11. 2024GraphStorm: all-in-one graph machine learning framework for industry applicationscited by 7
  12. 2024DiskGNN: Bridging I/O Efficiency and Model Accuracy for Out-of-Core GNN Trainingcited by 5
  13. 2024Can Graph Reordering Speed Up Graph Neural Network Training? An Experimental Studycited by 4
  14. 2024NeutronTP: Load-Balanced Distributed Full-Graph GNN Training with Tensor Parallelismcited by 4

Built on by

Not cited yet.