mlsanityData to 14 Oct 2026

PyTorch-BigGraph: A Large-scale Graph Embedding System

arXiv 1903.12287 ↗First posted 28 Mar 2019cs.LG cs.AI cs.DCcited by 119

Not on the map. Why?

Abstract (arXiv)

Graph embedding methods produce unsupervised node features from graphs that can then be used for a variety of machine learning tasks. Modern graphs, particularly in industrial applications, contain billions of nodes and trillions of edges, which exceeds the capability of existing embedding systems. We present PyTorch-BigGraph (PBG), an embedding system that incorporates several modifications to traditional multi-relation embedding systems that allow it to scale to graphs with billions of nodes and trillions of edges. PBG uses graph partitioning to train arbitrarily large embeddings on either a single machine or in a distributed environment. We demonstrate comparable performance with existing embedding systems on common benchmarks, while allowing for scaling to arbitrarily large graphs and parallelization on multiple machines. We train and evaluate embeddings on several large social network graphs as well as the full Freebase dataset, which contains over 100 million nodes and 2 billion edges.

Key facts. Cited by 119 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 29; 2022: 30; 2023: 25; 2024: 18; 2025: 11; 2026: 6.

119 papers.

Sort:

By area:

  1. 2022Graph Neural Networks for Link Prediction with Subgraph Sketchingcited by 81
  2. 2022Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddingscited by 75
  3. 2021NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphscited by 72
  4. 2023Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learningcited by 47
  5. 2022TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twittercited by 45
  6. 2022BNS-GCN: Efficient Full-Graph Training of Graph Convolutional Networks with Partition-Parallelism and Random Boundary Node Samplingcited by 43
  7. 2021Automated Machine Learning on Graphs: A Surveycited by 39
  8. 2022Modern Baselines for SPARQL Semantic Parsingcited by 34
  9. 2024LiGNN: Graph Neural Networks at LinkedIncited by 31
  10. 2021Marius: Learning Massive Graph Embeddings on a Single Machinecited by 29
  11. 2023CASSINI: Network-Aware Job Scheduling in Machine Learning Clusterscited by 26
  12. 2021Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledgecited by 24
38 more
  1. 2021Network Representation Learning: From Preprocessing, Feature Extraction to Node Embeddingcited by 19
  2. 2022MariusGNN: Resource-Efficient Out-of-Core Training of Graph Neural Networkscited by 19
  3. 2022Saga: A Platform for Continuous Construction and Serving of Knowledge At Scalecited by 19
  4. 2021SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphscited by 17
  5. 2023GrOVe: Ownership Verification of Graph Neural Networks using Embeddingscited by 16
  6. 2021AutoGL: A Library for Automated Graph Learningcited by 15
  7. 2021Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learningcited by 12
  8. 2021ScaleFreeCTR: MixCache-based Distributed Training System for CTR Models with Huge Embedding Tablecited by 12
  9. 2021GeoVectors: A Linked Open Corpus of OpenStreetMap Embeddings on World Scalecited by 12
  10. 2022Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directionscited by 9
  11. 2022Modeling Fine-grained Information via Knowledge-aware Hierarchical Graph for Zero-shot Entity Retrievalcited by 9
  12. 2023Friendly Neighbors: Contextualized Sequence-to-Sequence Link Predictioncited by 9
  13. 2024Negative Sampling in Knowledge Graph Representation Learning: A Reviewcited by 9
  14. 2021Cleora: A Simple, Strong and Scalable Graph Embedding Schemecited by 8
  15. 2022Augmenting Knowledge Graphs for Better Link Predictioncited by 7
  16. 2023Relevant Entity Selection: Knowledge Graph Bootstrapping via Zero-Shot Analogical Pruningcited by 7
  17. 2024Safety Control of Service Robots with LLMs and Embodied Knowledge Graphscited by 7
  18. 2024GraphStorm: all-in-one graph machine learning framework for industry applicationscited by 7
  19. 2021Large-Scale Network Embedding in Apache Sparkcited by 6
  20. 2022Efficient Heterogeneous Treatment Effect Estimation With Multiple Experiments and Multiple Outcomescited by 6
  21. 2023GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answeringcited by 6
  22. 2024AI and the Future of Digital Public Squarescited by 6
  23. 2021Learning Based Proximity Matrix Factorization for Node Embeddingcited by 5
  24. 2021Assessing the quality of sources in Wikidata across languages: a hybrid approachcited by 5
  25. 2022GROW: A Row-Stationary Sparse-Dense GEMM Accelerator for Memory-Efficient Graph Convolutional Neural Networkscited by 5
  26. 2023Knowledge Graphs Queryingcited by 5
  27. 2023Source-Aware Embedding Training on Heterogeneous Information Networkscited by 5
  28. 2023Linking Surface Facts to Large-Scale Knowledge Graphscited by 5
  29. 2021Knowledge Base Completion Meets Transfer Learningcited by 4
  30. 2022MEKER: Memory Efficient Knowledge Embedding Representation for Link Prediction and Question Answeringcited by 4
  31. 2022kNN-Embed: Locally Smoothed Embedding Mixtures For Multi-interest Candidate Retrievalcited by 4
  32. 2022Descartes: Generating Short Descriptions of Wikipedia Articlescited by 4
  33. 2022FairMILE: Towards an Efficient Framework for Fair Graph Representation Learningcited by 4
  34. 2023InferTurbo: A Scalable System for Boosting Full-graph Inference of Graph Neural Network over Huge Graphscited by 4
  35. 2023Multi-GPU Approach for Training of Graph ML Models on large CFD Meshescited by 4
  36. 2023MEGA: A Memory-Efficient GNN Accelerator Exploiting Degree-Aware Mixed-Precision Quantizationcited by 4
  37. 2024GraphScale: A Framework to Enable Machine Learning over Billion-node Graphscited by 4
  38. 2025OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learningcited by 4

50 most cited of 119 All 119 (JSON)