DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendation
This work improves production recommender systems for companies handling massive prediction volumes, though it appears incremental over DCNv2.
The authors tackled limitations in the Deep and Cross architecture (DCNv2) for large-scale recommendation systems by introducing three algorithmic improvements, resulting in DCN^2 which outperforms DCNv2 in offline and online tests while processing over 0.5 billion predictions per second.
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.