DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916812157878272 |
|---|---|
| author | Škrlj, Blaž Karni, Yonatan Gašperšič, Grega Mramor, Blaž Stolin, Yulia Jakomin, Martin Urbančič, Jasna Dishi, Yuval Silberstein, Natalia Friedler, Ophir Klein, Assaf |
| author_facet | Škrlj, Blaž Karni, Yonatan Gašperšič, Grega Mramor, Blaž Stolin, Yulia Jakomin, Martin Urbančič, Jasna Dishi, Yuval Silberstein, Natalia Friedler, Ophir Klein, Assaf |
| contents | The Deep and Cross architecture (DCNv2) is a robust production baseline and is integral to numerous real-life recommender systems. Its inherent efficiency and ability to model interactions often result in models that are both simpler and highly competitive compared to more computationally demanding alternatives, such as Deep FFMs. In this work, we introduce three significant algorithmic improvements to the DCNv2 architecture, detailing their formulation and behavior at scale. The enhanced architecture we refer to as DCN^2 is actively used in a live recommender system, processing over 0.5 billion predictions per second across diverse use cases where it out-performed DCNv2, both offline and online (ab tests). These improvements effectively address key limitations observed in the DCNv2, including information loss in Cross layers, implicit management of collisions through learnable lookup-level weights, and explicit modeling of pairwise similarities with a custom layer that emulates FFMs' behavior. The superior performance of DCN^2 is also demonstrated on four publicly available benchmark data sets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_21624 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendation Škrlj, Blaž Karni, Yonatan Gašperšič, Grega Mramor, Blaž Stolin, Yulia Jakomin, Martin Urbančič, Jasna Dishi, Yuval Silberstein, Natalia Friedler, Ophir Klein, Assaf Information Retrieval Machine Learning The Deep and Cross architecture (DCNv2) is a robust production baseline and is integral to numerous real-life recommender systems. Its inherent efficiency and ability to model interactions often result in models that are both simpler and highly competitive compared to more computationally demanding alternatives, such as Deep FFMs. In this work, we introduce three significant algorithmic improvements to the DCNv2 architecture, detailing their formulation and behavior at scale. The enhanced architecture we refer to as DCN^2 is actively used in a live recommender system, processing over 0.5 billion predictions per second across diverse use cases where it out-performed DCNv2, both offline and online (ab tests). These improvements effectively address key limitations observed in the DCNv2, including information loss in Cross layers, implicit management of collisions through learnable lookup-level weights, and explicit modeling of pairwise similarities with a custom layer that emulates FFMs' behavior. The superior performance of DCN^2 is also demonstrated on four publicly available benchmark data sets. |
| title | DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendation |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2506.21624 |