Exploring Scaling Laws of CTR Model for Online Performance Improvement

• URL: http://arxiv.org/abs/2508.15326v2
• Date: Fri, 19 Sep 2025 07:21:42 GMT
• Title: Exploring Scaling Laws of CTR Model for Online Performance Improvement
• Authors: Weijiang Lai, Beihong Jin, Jiongyan Zhang, Yiyuan Zheng, Jian Dong, Jia Cheng, Jun Lei, Xingxing Wang,
• Abstract summary: CTR models play a vital role in improving user experience and boosting business revenue in many online personalized services.<n>We propose a new paradigm for improving CTR predictions: first, constructing a CTR model with accuracy scalable to the model grade and data size, and then distilling the knowledge implied in this model into its lightweight model that can serve online users.<n> Experimental results show that SUAN performs exceptionally well and holds the scaling laws spanning three orders of magnitude in model grade and data size.
• Score: 16.56625869775141
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: CTR models play a vital role in improving user experience and boosting business revenue in many online personalized services. However, current CTR models generally encounter bottlenecks in performance improvement. Inspired by the scaling law phenomenon of LLMs, we propose a new paradigm for improving CTR predictions: first, constructing a CTR model with accuracy scalable to the model grade and data size, and then distilling the knowledge implied in this model into its lightweight model that can serve online users. To put it into practice, we construct a CTR model named SUAN (Stacked Unified Attention Network). In SUAN, we propose the UAB as a behavior sequence encoder. A single UAB unifies the modeling of the sequential and non-sequential features and also measures the importance of each user behavior feature from multiple perspectives. Stacked UABs elevate the configuration to a high grade, paving the way for performance improvement. In order to benefit from the high performance of the high-grade SUAN and avoid the disadvantage of its long inference time, we modify the SUAN with sparse self-attention and parallel inference strategies to form LightSUAN, and then adopt online distillation to train the low-grade LightSUAN, taking a high-grade SUAN as a teacher. The distilled LightSUAN has superior performance but the same inference time as the LightSUAN, making it well-suited for online deployment. Experimental results show that SUAN performs exceptionally well and holds the scaling laws spanning three orders of magnitude in model grade and data size, and the distilled LightSUAN outperforms the SUAN configured with one grade higher. More importantly, the distilled LightSUAN has been integrated into an online service, increasing the CTR by 2.81% and CPM by 1.69% while keeping the average inference time acceptable. Our source code is available at https://github.com/laiweijiang/SUAN.

Related papers

• Scaling Transformers for Discriminative Recommendation via Generative Pretraining [15.796591192359044]
  We propose a framework named GPSD (textbfGenerative textbfPretraining for textbfScalable textbfDiscriminative Recommendation) to address the overfitting issue.<n>Extensive experiments conducted on both industrial-scale and publicly available datasets demonstrate the superior performance of GPSD.
  arXiv  Detail & Related papers  (2025-06-04T08:31:33Z)
• Diffusion Guidance Is a Controllable Policy Improvement Operator [98.11511661904618]
  CFGRL is trained with the simplicity of supervised learning, yet can further improve on the policies in the data.<n>On offline RL tasks, we observe a reliable trend -- increased guidance weighting leads to increased performance.
  arXiv  Detail & Related papers  (2025-05-29T14:06:50Z)
• Enhancing Training Data Attribution with Representational Optimization [57.61977909113113]
  Training data attribution methods aim to measure how training data impacts a model's predictions.<n>We propose AirRep, a representation-based approach that closes this gap by learning task-specific and model-aligned representations explicitly for TDA.<n>AirRep introduces two key innovations: a trainable encoder tuned for attribution quality, and an attention-based pooling mechanism that enables accurate estimation of group-wise influence.
  arXiv  Detail & Related papers  (2025-05-24T05:17:53Z)
• Balancing Efficiency and Effectiveness: An LLM-Infused Approach for Optimized CTR Prediction [19.657522015829922]
  We introduce a novel approach that models deep semantic information end-to-end.<n>Our framework is carefully designed to balance efficiency and effectiveness.<n>Online A/B tests conducted on the Meituan sponsored-search system demonstrate that our method significantly outperforms baseline models in terms of Cost Per Mile (CPM) and Click Through Rate (CTR)
  arXiv  Detail & Related papers  (2024-12-09T02:36:38Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping [53.454408491386886]
  bootstrapping self-alignment markedly surpasses the single-round approach. We propose Step-On-Feet Tuning (SOFT) which leverages model's continuously enhanced few-shot ability to boost zero or one-shot performance. Based on easy-to-hard training recipe, we propose SOFT+ which further boost self-alignment's performance.
  arXiv  Detail & Related papers  (2024-02-12T12:30:42Z)
• Uncovering the Hidden Cost of Model Compression [43.62624133952414]
  Visual Prompting has emerged as a pivotal method for transfer learning in computer vision. Model compression detrimentally impacts the performance of visual prompting-based transfer. However, negative effects on calibration are not present when models are compressed via quantization.
  arXiv  Detail & Related papers  (2023-08-29T01:47:49Z)
• E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning [55.50908600818483]
  Fine-tuning large-scale pretrained vision models for new tasks has become increasingly parameter-intensive. We propose an Effective and Efficient Visual Prompt Tuning (E2VPT) approach for large-scale transformer-based model adaptation. Our approach outperforms several state-of-the-art baselines on two benchmarks.
  arXiv  Detail & Related papers  (2023-07-25T19:03:21Z)
• Directed Acyclic Graph Factorization Machines for CTR Prediction via Knowledge Distillation [65.62538699160085]
  We propose a Directed Acyclic Graph Factorization Machine (KD-DAGFM) to learn the high-order feature interactions from existing complex interaction models for CTR prediction via Knowledge Distillation. KD-DAGFM achieves the best performance with less than 21.5% FLOPs of the state-of-the-art method on both online and offline experiments.
  arXiv  Detail & Related papers  (2022-11-21T03:09:42Z)
• Efficient Long Sequential User Data Modeling for Click-Through Rate Prediction [9.455385139394494]
  We propose an end-to-end paradigm to model long behavior sequences, which is able to achieve superior performance and remarkable cost-efficiency. Our contribution is three-fold: First, we propose a hashing-based efficient target attention (TA) network named ETA-Net to enable end-to-end user behavior retrieval. ETA-Net has been deployed on the recommender system of Taobao, and brought 1.8% lift on CTR and 3.1% lift on Gross Merchandise Value (GMV) compared to the SOTA two-stage methods.
  arXiv  Detail & Related papers  (2022-09-25T12:59:57Z)

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.