# ML-DCN: Masked Low-Rank Deep Crossing Network Towards Scalable Ads Click-through Rate Prediction at Pinterest

arXiv: https://arxiv.org/abs/2602.09194 · HTML: https://mlsanity.com/paper/2602.09194/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 16 of 16)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [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)
- [Learning Factored Representations in a Deep Mixture of Experts](https://mlsanity.com/paper/1312.4314/) (2013)
- [xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems](https://mlsanity.com/paper/1803.05170/) (2018)
- [FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction](https://mlsanity.com/paper/1905.09433/) (2019)
- [PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest](https://mlsanity.com/paper/2007.03634/) (2020)
- [Wukong: Towards a Scaling Law for Large-Scale Recommendation](https://mlsanity.com/paper/2403.02545/) (2024)
- [Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions](https://mlsanity.com/paper/1909.03276/) (2019)
- [MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask](https://mlsanity.com/paper/2102.07619/) (2021)
- [RankMixer: Scaling Up Ranking Models in Industrial Recommenders](https://mlsanity.com/paper/2507.15551/) (2025)
- [Learning to Embed Categorical Features without Embedding Tables for Recommendation](https://mlsanity.com/paper/2010.10784/) (2020)

## Abstract (arXiv)

Deep learning recommendation systems rely on feature interaction modules to model complex user-item relationships across sparse categorical and dense features. In large-scale ad ranking, increasing model capacity is a promising path to improving both predictive performance and business outcomes, yet production serving budgets impose strict constraints on latency and FLOPs. This creates a central tension: we want interaction modules that both scale effectively with additional compute and remain compute-efficient at serving time. In this work, we study how to scale feature interaction modules under a fixed serving budget. We find that naively scaling DCNv2 and MaskNet, despite their widespread adoption in industry, yields rapidly diminishing offline gains in the Pinterest ads ranking system. To overcome aforementioned limitations, we propose ML-DCN, an interaction module that integrates an instance-conditioned mask into a low-rank crossing layer, enabling per-example selection and amplification of salient interaction directions while maintaining efficient computation. This novel architecture combines the strengths of DCNv2 and MaskNet, scales efficiently with increased compute, and achieves state-of-the-art performance. Experiments on a large internal Pinterest ads dataset show that ML-DCN achieves higher AUC than DCNv2, MaskNet, and recent scaling-oriented alternatives at matched FLOPs, and it scales more favorably overall as compute increases, exhibiting a stronger AUC-FLOPs trade-off. Finally, online A/B tests demonstrate statistically significant improvements in key ads metrics (including CTR and click-quality measures) and ML-DCN has been deployed in the production system with neutral serving cost.