mlsanityData to 14 Oct 2026

OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learning

arXiv 2504.17811 ↗First posted 22 Apr 2025cs.IR cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Representation learning, a task of learning latent vectors to represent entities, is a key task in improving search and recommender systems in web applications. Various representation learning methods have been developed, including graph-based approaches for relationships among entities, sequence-based methods for capturing the temporal evolution of user activities, and content-based models for leveraging text and visual content. However, the development of a unifying framework that integrates these diverse techniques to support multiple applications remains a significant challenge. This paper presents OmniSage, a large-scale representation framework that learns universal representations for a variety of applications at Pinterest. OmniSage integrates graph neural networks with content-based models and user sequence models by employing multiple contrastive learning tasks to effectively process graph data, user sequence data, and content signals. To support the training and inference of OmniSage, we developed an efficient infrastructure capable of supporting Pinterest graphs with billions of nodes. The universal representations generated by OmniSage have significantly enhanced user experiences on Pinterest, leading to an approximate 2.5% increase in sitewide repins (saves) across five applications. This paper highlights the impact of unifying representation learning methods, and we make the model code publicly available at https://github.com/pinterest/atg-research/tree/main/omnisage.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 35 of its 55 references that are in the map. First posted on arXiv 22 Apr 2025.

Builds on

35 of 55 references.

References · 35

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2017Graph Attention Networkscited by 8,923
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2017Inductive Representation Learning on Large Graphscited by 6,320
  8. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  9. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  10. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  11. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  12. 2019Heterogeneous Graph Attention Networkcited by 734
23 more
  1. 2019Graph Neural Networks for Social Recommendationcited by 714
  2. 2019Graph Transformer Networkscited by 523
  3. 2022Multimodal Learning with Transformers: A Surveycited by 400
  4. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 372
  5. 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendationscited by 188
  6. 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
  7. 2019AliGraph: A Comprehensive Graph Neural Network Platformcited by 153
  8. 2021Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learningcited by 130
  9. 2020A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sourcescited by 126
  10. 2019PyTorch-BigGraph: A Large-scale Graph Embedding Systemcited by 119
  11. 2020PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterestcited by 75
  12. 2022Simple and Efficient Heterogeneous Graph Neural Networkcited by 71
  13. 2022PinnerFormer: Sequence Modeling for User Representation at Pinterestcited by 57
  14. 2017Hash Embeddings for Efficient Word Representationscited by 55
  15. 2023TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterestcited by 35
  16. 2022MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initializationcited by 31
  17. 2024LiGNN: Graph Neural Networks at LinkedIncited by 31
  18. 2020Graph Enhanced Representation Learning for News Recommendationcited by 30
  19. 2021Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representationscited by 24
  20. 2022ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterestcited by 23
  21. 2024OmniSearchSage: Multi-Task Multi-Entity Embeddings for Pinterest Searchcited by 13
  22. 2024GraphStorm: all-in-one graph machine learning framework for industry applicationscited by 7
  23. 2024USE: Dynamic User Modeling with Stateful Sequence Modelscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025HGCL: Hierarchical Graph Contrastive Learning for User-Item Recommendationcited by 1
  2. 2026UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scalecited by 1
  3. 2026Pinterest Canvas: Large-Scale Image Generation at Pinterestcited by 0
  4. 2026A Multi-Source Ensemble Approach to Candidate Generation for Alternative Vacation Rental Property Recommendationscited by 0