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

• URL: http://arxiv.org/abs/2602.09194v1
• Date: Mon, 09 Feb 2026 20:59:19 GMT
• Title: ML-DCN: Masked Low-Rank Deep Crossing Network Towards Scalable Ads Click-through Rate Prediction at Pinterest
• Abstract summary: We study how to scale feature interaction modules under a fixed serving budget.<n>We propose ML-DCN, an interaction module that integrates an instance-conditioned mask into a low-rank crossing layer.<n>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.
• Score: 10.393086325256974
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Boosting Neural Video Codec via Scale-Driven Online Flow Refinement [59.68390983151205]
  We propose a Training-Free Scale-Driven Online Flow Refinement (SOFR) method.<n>It fuses motion information from coarse and fine scales according to warping accuracy, effectively rectifying motion estimation errors.<n>It brings an average of 2.84% and 4.05% savings in terms of PSNR and MS-SSIM, respectively.
  arXiv  Detail & Related papers  (2026-06-22T08:36:23Z)
• Compress, Cross and Scale: Multi-Level Compression Cross Networks for Efficient Scaling in Recommender Systems [5.897678894426804]
  MLCC is a structured feature interaction architecture that organizes feature crosses through hierarchical compression and dynamic composition.<n>MC-MLCC is a Multi-Channel extension that decomposes feature interactions into parallel subspaces.<n>Our proposed models consistently outperform strong DLRM-style baselines by up to 0.52 AUC, while reducing model parameters and FLOPs by up to 26$times$ under comparable performance.
  arXiv  Detail & Related papers  (2026-02-12T15:06:46Z)
• Explicit Multi-head Attention for Inter-head Interaction in Large Language Models [70.96854312026319]
  Multi-head Explicit Attention (MEA) is a simple yet effective attention variant that explicitly models cross-head interaction.<n>MEA shows strong robustness in pretraining, which allows the use of larger learning rates that lead to faster convergence.<n>This enables a practical key-value cache compression strategy that reduces KV-cache memory usage by 50% with negligible performance loss.
  arXiv  Detail & Related papers  (2026-01-27T13:45:03Z)
• DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendation [1.1027313935007121]
  We introduce three significant algorithmic improvements to the DCNv2 architecture, detailing their formulation and behavior at scale.<n>The enhanced architecture we refer to as DCN2 is actively used in a live recommender system, processing over 0.5 billion predictions per second across diverse use cases.<n>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.
  arXiv  Detail & Related papers  (2025-06-24T06:44:42Z)
• MID-L: Matrix-Interpolated Dropout Layer with Layer-wise Neuron Selection [0.0]
  Matrix-Interpolated Dropout Layer (MID-L) dynamically selects and activates only the most informative neurons.<n>Experiments on six benchmarks, including MNIST, CIFAR-10, CIFAR-100, SVHN, UCI Adult, and IMDB, show that MID-L achieves up to average 55% reduction in active neurons.
  arXiv  Detail & Related papers  (2025-05-16T16:29:19Z)
• ALWNN Empowered Automatic Modulation Classification: Conquering Complexity and Scarce Sample Conditions [24.59462798452397]
  This paper proposes an automatic modulation classification model based on the Adaptive Lightweight Wavelet Neural Network (ALWNN) and the few-shot framework (MALWNN)<n>The ALWNN model, by integrating the adaptive wavelet neural network and depth separable convolution, reduces the number of model parameters and computational complexity.<n> Experiments with MALWNN show its superior performance in few-shot learning scenarios compared to other algorithms.
  arXiv  Detail & Related papers  (2025-03-24T06:14:33Z)
• Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design [59.00758127310582]
  We propose a novel framework Read-ME that transforms pre-trained dense LLMs into smaller MoE models. Our approach employs activation sparsity to extract experts. Read-ME outperforms other popular open-source dense models of similar scales.
  arXiv  Detail & Related papers  (2024-10-24T19:48:51Z)
• A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading [62.34538208323411]
  We propose a multi-head ensemble multi-task learning (MEMTL) approach with a shared backbone and multiple prediction heads (PHs) MEMTL outperforms benchmark methods in both the inference accuracy and mean square error without requiring additional training data.
  arXiv  Detail & Related papers  (2023-09-02T11:01:16Z)
• Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyML [4.2019872499238256]
  We propose a novel strategy for deploying deep neural networks on microcontrollers (TinyML) based on multi-objective Bayesian optimization (MOBOpt)<n>Our methodology aims at efficiently finding tradeoffs between a DNN's predictive accuracy, memory requirements on a given target system, and computational complexity.
  arXiv  Detail & Related papers  (2023-05-23T14:31:52Z)
• Neural Attentive Circuits [93.95502541529115]
  We introduce a general purpose, yet modular neural architecture called Neural Attentive Circuits (NACs) NACs learn the parameterization and a sparse connectivity of neural modules without using domain knowledge. NACs achieve an 8x speedup at inference time while losing less than 3% performance.
  arXiv  Detail & Related papers  (2022-10-14T18:00:07Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)
• Optimization-driven Machine Learning for Intelligent Reflecting Surfaces Assisted Wireless Networks [82.33619654835348]
  Intelligent surface (IRS) has been employed to reshape the wireless channels by controlling individual scattering elements' phase shifts. Due to the large size of scattering elements, the passive beamforming is typically challenged by the high computational complexity. In this article, we focus on machine learning (ML) approaches for performance in IRS-assisted wireless networks.
  arXiv  Detail & Related papers  (2020-08-29T08:39:43Z)
• DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems [15.398542784403604]
  Deep & Cross Network (DCN) was proposed to automatically and efficiently learn bounded-degree predictive feature interactions. We propose an improved framework DCN-V2 to make DCN more practical in large-scale industrial settings.
  arXiv  Detail & Related papers  (2020-08-19T20:33:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.