Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.00584 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917601680031744 |
|---|---|
| author | Fazelnia, Ghazal Gupta, Sanket Keum, Claire Koh, Mark Anderson, Ian Lalmas, Mounia |
| author_facet | Fazelnia, Ghazal Gupta, Sanket Keum, Claire Koh, Mark Anderson, Ian Lalmas, Mounia |
| contents | We present a novel framework for user representation in large-scale recommender systems, aiming at effectively representing diverse user taste in a generalized manner. Our approach employs a two-stage methodology combining representation learning and transfer learning. The representation learning model uses an autoencoder that compresses various user features into a representation space. In the second stage, downstream task-specific models leverage user representations via transfer learning instead of curating user features individually. We further augment this methodology on the representation's input features to increase flexibility and enable reaction to user events, including new user experiences, in Near-Real Time. Additionally, we propose a novel solution to manage deployment of this framework in production models, allowing downstream models to work independently. We validate the performance of our framework through rigorous offline and online experiments within a large-scale system, showcasing its remarkable efficacy across multiple evaluation tasks. Finally, we show how the proposed framework can significantly reduce infrastructure costs compared to alternative approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_00584 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generalized User Representations for Transfer Learning Fazelnia, Ghazal Gupta, Sanket Keum, Claire Koh, Mark Anderson, Ian Lalmas, Mounia Information Retrieval Machine Learning We present a novel framework for user representation in large-scale recommender systems, aiming at effectively representing diverse user taste in a generalized manner. Our approach employs a two-stage methodology combining representation learning and transfer learning. The representation learning model uses an autoencoder that compresses various user features into a representation space. In the second stage, downstream task-specific models leverage user representations via transfer learning instead of curating user features individually. We further augment this methodology on the representation's input features to increase flexibility and enable reaction to user events, including new user experiences, in Near-Real Time. Additionally, we propose a novel solution to manage deployment of this framework in production models, allowing downstream models to work independently. We validate the performance of our framework through rigorous offline and online experiments within a large-scale system, showcasing its remarkable efficacy across multiple evaluation tasks. Finally, we show how the proposed framework can significantly reduce infrastructure costs compared to alternative approaches. |
| title | Generalized User Representations for Transfer Learning |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2403.00584 |