mlsanityData to 7 Oct 2026

Layer-Neighbor Sampling -- Defusing Neighborhood Explosion in GNNs

arXiv 2210.13339 ↗First posted 24 Oct 2022cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have received significant attention recently, but training them at a large scale remains a challenge. Mini-batch training coupled with sampling is used to alleviate this challenge. However, existing approaches either suffer from the neighborhood explosion phenomenon or have poor performance. To address these issues, we propose a new sampling algorithm called LAyer-neighBOR sampling (LABOR). It is designed to be a direct replacement for Neighbor Sampling (NS) with the same fanout hyperparameter while sampling up to 7 times fewer vertices, without sacrificing quality. By design, the variance of the estimator of each vertex matches NS from the point of view of a single vertex. Moreover, under the same vertex sampling budget constraints, LABOR converges faster than existing layer sampling approaches and can use up to 112 times larger batch sizes compared to NS.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 23 of its 36 references that are in the map. First posted on arXiv 24 Oct 2022.

Builds on

23 of 36 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  7. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  8. 2021How Attentive are Graph Attention Networks?cited by 818
  9. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  10. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  11. 2020Heterogeneous Graph Transformercited by 581
  12. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
11 more
  1. 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
  2. 2019Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networkscited by 177
  3. 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
  4. 2021GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddingscited by 90
  5. 2021Distributed Hybrid CPU and GPU training for Graph Neural Networks on Billion-Scale Graphscited by 33
  6. 2020Bandit Samplers for Training Graph Neural Networkscited by 30
  7. 2021Global Neighbor Sampling for Mixed CPU-GPU Training on Giant Graphscited by 22
  8. 2021A Biased Graph Neural Network Sampler with Near-Optimal Regretcited by 17
  9. 2021Adaptive normalization for IPW estimationcited by 7
  10. 2022Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networkscited by 5
  11. 2021On the Importance of Sampling in Training GCNs: Tighter Analysis and Variance Reductioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 5; 2025: 8; 2026: 4.

19 papers.

Sort:

  1. 2025GraphPFN: A Prior-Data Fitted Graph Foundation Modelcited by 20
  2. 2024Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matchingcited by 8
  3. 2024A Scalable and Effective Alternative to Graph Transformerscited by 4
  4. 2024MassiveGNN: Efficient Training via Prefetching for Massively Connected Distributed Graphscited by 3
  5. 2025Accurate and Scalable Graph Neural Networks via Message Invariancecited by 3
  6. 2025LMAE4Eth: Generalizable and Robust Ethereum Fraud Detection by Exploring Transaction Semantics and Masked Graph Embeddingcited by 3
  7. 2023A Local Graph Limits Perspective on Sampling-Based GNNscited by 2
  8. 2025Graph Learning at Scale: Characterizing and Optimizing Pre-Propagation GNNscited by 2
  9. 2025Efficient GNN Training Through Structure-Aware Randomized Mini-Batchingcited by 2
  10. 2024PromptGCN: Bridging Subgraph Gaps in Lightweight GCNscited by 1
  11. 2026Implicit Regularization of Mini-Batch Training in Graph Neural Networkscited by 1
  12. 2023Cooperative Minibatching in Graph Neural Networkscited by 0
7 more
  1. 2024Vision Paper: Designing Graph Neural Networks in Compliance with the European Artificial Intelligence Actcited by 0
  2. 2025Enhanced Soups for Graph Neural Networkscited by 0
  3. 2025ATLAS: Adaptive Topology-based Learning at Scale for Homophilic and Heterophilic Graphscited by 0
  4. 2025BLISS: Bandit Layer Importance Sampling Strategy for Efficient Training of Graph Neural Networkscited by 0
  5. 2026Weighted Graph Clustering via Scale Contraction and Graph Structure Learningcited by 0
  6. 2026KidMesh: Computational Mesh Reconstruction for Pediatric Congenital Hydronephrosis Using Deep Neural Networkscited by 0
  7. 2026MetaSieve: Faster Relational Deep Learning through SQL-Based Metapath Selectioncited by 0