# DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendation

arXiv: https://arxiv.org/abs/2506.21624 · HTML: https://mlsanity.com/paper/2506.21624/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 19 references that are in the map.
- First posted on arXiv 24 Jun 2025.

## Builds on (most cited first, 15 of 15)

- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems](https://mlsanity.com/paper/2008.13535/) (2020)
- [AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks](https://mlsanity.com/paper/1810.11921/) (2018)
- [Recommender Systems in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2307.02046/) (2023)
- [Polysemanticity and Capacity in Neural Networks](https://mlsanity.com/paper/2210.01892/) (2022)
- [Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising](https://mlsanity.com/paper/1806.03514/) (2018)
- [Higher-Order Factorization Machines](https://mlsanity.com/paper/1607.07195/) (2016)
- [Monolith: Real Time Recommendation System With Collisionless Embedding Table](https://mlsanity.com/paper/2209.07663/) (2022)
- [Real-Time Bidding Benchmarking with iPinYou Dataset](https://mlsanity.com/paper/1407.7073/) (2014)
- [Enhancing Embedding Representation Stability in Recommendation Systems with Semantic ID](https://mlsanity.com/paper/2504.02137/) (2025)
- [Embedding Compression in Recommender Systems: A Survey](https://mlsanity.com/paper/2408.02304/) (2024)
- [GraphFM: Graph Factorization Machines for Feature Interaction Modeling](https://mlsanity.com/paper/2105.11866/) (2021)
- [Fully Understanding the Hashing Trick](https://mlsanity.com/paper/1805.08539/) (2018)
- [Learning to Collide: Recommendation System Model Compression with Learned Hash Functions](https://mlsanity.com/paper/2203.15837/) (2022)
- [A Bag of Tricks for Scaling CPU-based Deep FFMs to more than 300m Predictions per Second](https://mlsanity.com/paper/2407.10115/) (2024)

## Abstract (arXiv)

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.