OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915338669522944 |
|---|---|
| author | Badrinath, Anirudhan Yang, Alex Rajesh, Kousik Agarwal, Prabhat Yang, Jaewon Chen, Haoyu Xu, Jiajing Rosenberg, Charles |
| author_facet | Badrinath, Anirudhan Yang, Alex Rajesh, Kousik Agarwal, Prabhat Yang, Jaewon Chen, Haoyu Xu, Jiajing Rosenberg, Charles |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17811 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learning Badrinath, Anirudhan Yang, Alex Rajesh, Kousik Agarwal, Prabhat Yang, Jaewon Chen, Haoyu Xu, Jiajing Rosenberg, Charles Information Retrieval Machine Learning 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. |
| title | OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learning |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2504.17811 |