mlsanityData to 14 Oct 2026

LiGNN: Graph Neural Networks at LinkedIn

arXiv 2402.11139 ↗First posted 17 Feb 2024cs.LG cs.AIcited by 31

Not on the map. Why?

Abstract (arXiv)

In this paper, we present LiGNN, a deployed large-scale Graph Neural Networks (GNNs) Framework. We share our insight on developing and deployment of GNNs at large scale at LinkedIn. We present a set of algorithmic improvements to the quality of GNN representation learning including temporal graph architectures with long term losses, effective cold start solutions via graph densification, ID embeddings and multi-hop neighbor sampling. We explain how we built and sped up by 7x our large-scale training on LinkedIn graphs with adaptive sampling of neighbors, grouping and slicing of training data batches, specialized shared-memory queue and local gradient optimization. We summarize our deployment lessons and learnings gathered from A/B test experiments. The techniques presented in this work have contributed to an approximate relative improvements of 1% of Job application hearing back rate, 2% Ads CTR lift, 0.5% of Feed engaged daily active users, 0.2% session lift and 0.1% weekly active user lift from people recommendation. We believe that this work can provide practical solutions and insights for engineers who are interested in applying Graph neural networks at large scale.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 24 of its 34 references that are in the map. First posted on arXiv 17 Feb 2024.

Builds on

24 of 34 references.

References · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2018How Powerful are Graph Neural Networks?cited by 4,393
  4. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  5. 2017Mixed Precision Trainingcited by 1,156
  6. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  7. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 530
  8. 2018Generating Wikipedia by Summarizing Long Sequencescited by 335
  9. 2014One weird trick for parallelizing convolutional neural networkscited by 264
  10. 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
  11. 2020Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A surveycited by 124
  12. 2019PyTorch-BigGraph: A Large-scale Graph Embedding Systemcited by 119
12 more
  1. 2022PinnerFormer: Sequence Modeling for User Representation at Pinterestcited by 57
  2. 2023Relational Deep Learning: Graph Representation Learning on Relational Databasescited by 56
  3. 2020Pre-Training Graph Neural Networks for Cold-Start Users and Items Representationcited by 42
  4. 2022MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initializationcited by 31
  5. 2020Grale: Designing Networks for Graph Learningcited by 28
  6. 2021Heterogeneous Graph Neural Networks for Large-Scale Bid Keyword Matchingcited by 6
  7. 2021A Multi-Strategy based Pre-Training Method for Cold-Start Recommendationcited by 5
  8. 2023Uncertainty-aware Consistency Learning for Cold-Start Item Recommendationcited by 5
  9. 2020LANNS: A Web-Scale Approximate Nearest Neighbor Lookup Systemcited by 4
  10. 2023adSformers: Personalization from Short-Term Sequences and Diversity of Representations in Etsy Adscited by 4
  11. 2022NxtPost: User to Post Recommendations in Facebook Groupscited by 3
  12. 2023HUGE: Huge Unsupervised Graph Embeddings with TPUscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 9; 2025: 13; 2026: 9.

31 papers.

Sort:

By area:

  1. 2024Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insightscited by 44
  2. 2024One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphscited by 12
  3. 2025GiGL: Large-Scale Graph Neural Networks at Snapchatcited by 8
  4. 2024Valid Conformal Prediction for Dynamic GNNscited by 6
  5. 2024On the H"older Stability of Multiset and Graph Neural Networkscited by 6
  6. 2024Graph Neural Networks on Quantum Computerscited by 4
  7. 2025OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learningcited by 4
  8. 2025Simple yet Effective Graph Distillation via Clusteringcited by 4
  9. 2026A Fair Evaluation of Graph Foundation Models for Node Property Predictioncited by 4
  10. 2024LinkedIn Post Embeddings: Industrial Scale Embedding Generation and Usage across LinkedIncited by 2
  11. 2024LiNR: Model Based Neural Retrieval on GPUs at LinkedIncited by 2
  12. 2025Partition-wise Graph Filtering: A Unified Perspective Through the Lens of Graph Coarseningcited by 2
19 more
  1. 2025Understanding Generalization in Node and Link Predictioncited by 2
  2. 2025A Scalable and Efficient Signal Integration System for Job Matchingcited by 2
  3. 2024Polynomial Selection in Spectral Graph Neural Networks: An Error-Sum of Function Slices Approachcited by 1
  4. 2025Inductive Graph Representation Learning with Quantum Graph Neural Networkscited by 1
  5. 2025HGCL: Hierarchical Graph Contrastive Learning for User-Item Recommendationcited by 1
  6. 2025Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networkscited by 1
  7. 2026Generalizing GNNs with Tokenized Mixture of Expertscited by 1
  8. 2026Memory Is No Longer a Bottleneck: Memory-Efficient Graph Filtering for Scalable Collaborative Filteringcited by 1
  9. 2024Graph Transductive Defense: a Two-Stage Defense for Graph Membership Inference Attackscited by 0
  10. 2025IRA: Adaptive Interest-aware Representation and Alignment for Personalized Multi-interest Retrievalcited by 0
  11. 2025Large Scalable Cross-Domain Graph Neural Networks for Personalized Notification at LinkedIncited by 0
  12. 2025Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentationscited by 0
  13. 2025Enhancing Graph Neural Networks: A Mutual Learning Approachcited by 0
  14. 2026Coden: Efficient Temporal Graph Neural Networks for Continuous Predictioncited by 0
  15. 2026k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPScited by 0
  16. 2026RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendationcited by 0
  17. 2026Efficient Recommendations via Graph Coarsening and Label Propagationcited by 0
  18. 2026Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Samplingcited by 0
  19. 2026Hybrid GPU-CPU Retrieval for Personalized Search at Ultra-Large Scalecited by 0