Async Learned User Embeddings for Ads Delivery Optimization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914846532960256 |
|---|---|
| author | Tang, Mingwei Liu, Meng Li, Hong Yang, Junjie Wei, Chenglin Li, Boyang Li, Dai Xu, Rengan Xu, Yifan Zhang, Zehua Wang, Xiangyu Liu, Linfeng Xie, Yuelei Liu, Chengye Fawaz, Labib Li, Li Wang, Hongnan Zhu, Bill Reddy, Sri |
| author_facet | Tang, Mingwei Liu, Meng Li, Hong Yang, Junjie Wei, Chenglin Li, Boyang Li, Dai Xu, Rengan Xu, Yifan Zhang, Zehua Wang, Xiangyu Liu, Linfeng Xie, Yuelei Liu, Chengye Fawaz, Labib Li, Li Wang, Hongnan Zhu, Bill Reddy, Sri |
| contents | In recommendation systems, high-quality user embeddings can capture subtle preferences, enable precise similarity calculations, and adapt to changing preferences over time to maintain relevance. The effectiveness of recommendation systems depends on the quality of user embedding. We propose to asynchronously learn high fidelity user embeddings for billions of users each day from sequence based multimodal user activities through a Transformer-like large scale feature learning module. The async learned user representations embeddings (ALURE) are further converted to user similarity graphs through graph learning and then combined with user realtime activities to retrieval highly related ads candidates for the ads delivery system. Our method shows significant gains in both offline and online experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_05898 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Async Learned User Embeddings for Ads Delivery Optimization Tang, Mingwei Liu, Meng Li, Hong Yang, Junjie Wei, Chenglin Li, Boyang Li, Dai Xu, Rengan Xu, Yifan Zhang, Zehua Wang, Xiangyu Liu, Linfeng Xie, Yuelei Liu, Chengye Fawaz, Labib Li, Li Wang, Hongnan Zhu, Bill Reddy, Sri Information Retrieval Artificial Intelligence Machine Learning In recommendation systems, high-quality user embeddings can capture subtle preferences, enable precise similarity calculations, and adapt to changing preferences over time to maintain relevance. The effectiveness of recommendation systems depends on the quality of user embedding. We propose to asynchronously learn high fidelity user embeddings for billions of users each day from sequence based multimodal user activities through a Transformer-like large scale feature learning module. The async learned user representations embeddings (ALURE) are further converted to user similarity graphs through graph learning and then combined with user realtime activities to retrieval highly related ads candidates for the ads delivery system. Our method shows significant gains in both offline and online experiments. |
| title | Async Learned User Embeddings for Ads Delivery Optimization |
| topic | Information Retrieval Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2406.05898 |