# APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction

arXiv: https://arxiv.org/abs/2203.16218 · HTML: https://mlsanity.com/paper/2203.16218/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 45 references that are in the map.
- First posted on arXiv 30 Mar 2022.

## Builds on (most cited first, 30 of 32)

- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Cross-stitch Networks for Multi-task Learning](https://mlsanity.com/paper/1604.03539/) (2016)
- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [Measuring the Intrinsic Dimension of Objective Landscapes](https://mlsanity.com/paper/1804.08838/) (2018)
- [AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks](https://mlsanity.com/paper/1810.11921/) (2018)
- [Dynamic Filter Networks](https://mlsanity.com/paper/1605.09673/) (2016)
- [Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks](https://mlsanity.com/paper/2106.04489/) (2021)
- [ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks](https://mlsanity.com/paper/1908.03930/) (2019)
- [Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction](https://mlsanity.com/paper/2006.05639/) (2020)
- [Conditional Computation in Neural Networks for faster models](https://mlsanity.com/paper/1511.06297/) (2015)
- [Product-based Neural Networks for User Response Prediction](https://mlsanity.com/paper/1611.00144/) (2016)
- [Knowledge Graph Convolutional Networks for Recommender Systems](https://mlsanity.com/paper/1904.12575/) (2019)
- [MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation](https://mlsanity.com/paper/1908.00413/) (2019)
- [Diverse Branch Block: Building a Convolution as an Inception-like Unit](https://mlsanity.com/paper/2103.13425/) (2021)
- [FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction](https://mlsanity.com/paper/1905.09433/) (2019)
- [One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction](https://mlsanity.com/paper/2101.11427/) (2021)
- [Contextual Parameter Generation for Universal Neural Machine Translation](https://mlsanity.com/paper/1808.08493/) (2018)
- [Neural Input Search for Large Scale Recommendation Models](https://mlsanity.com/paper/1907.04471/) (2019)
- [Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction](https://mlsanity.com/paper/2007.06434/) (2020)
- [Deep Learning for Click-Through Rate Estimation](https://mlsanity.com/paper/2104.10584/) (2021)
- [Exponentially Increasing the Capacity-to-Computation Ratio for Conditional Computation in Deep Learning](https://mlsanity.com/paper/1406.7362/) (2014)
- [IntentGC: a Scalable Graph Convolution Framework Fusing Heterogeneous Information for Recommendation](https://mlsanity.com/paper/1907.12377/) (2019)
- [S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search](https://mlsanity.com/paper/1911.07033/) (2019)
- [Click-Through Rate Prediction with Multi-Modal Hypergraphs](https://mlsanity.com/paper/2109.02398/) (2021)
- [Decouple Learning for Parameterized Image Operators](https://mlsanity.com/paper/1807.08186/) (2018)

## Built on by (most cited first, 12 of 12)

- [AdaSparse: Learning Adaptively Sparse Structures for Multi-Domain Click-Through Rate Prediction](https://mlsanity.com/paper/2206.13108/) (2022)
- [Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions](https://mlsanity.com/paper/2209.15409/) (2022)
- [Hate Speech Detection with Generalizable Target-aware Fairness](https://mlsanity.com/paper/2406.00046/) (2024)
- [BASM: A Bottom-up Adaptive Spatiotemporal Model for Online Food Ordering Service](https://mlsanity.com/paper/2211.12033/) (2022)
- [Hybrid Contrastive Constraints for Multi-Scenario Ad Ranking](https://mlsanity.com/paper/2302.02636/) (2023)
- [GPRec: Bi-level User Modeling for Deep Recommenders](https://mlsanity.com/paper/2410.20730/) (2024)
- [DIGMN: Dynamic Intent Guided Meta Network for Differentiated User Engagement Forecasting in Online Professional Social Platforms](https://mlsanity.com/paper/2210.12402/) (2022)
- [FAN: Fatigue-Aware Network for Click-Through Rate Prediction in E-commerce Recommendation](https://mlsanity.com/paper/2304.04529/) (2023)
- [DynInt: Dynamic Interaction Modeling for Large-scale Click-Through Rate Prediction](https://mlsanity.com/paper/2301.08139/) (2023)
- [DPAN: Dynamic Preference-based and Attribute-aware Network for Relevant Recommendations](https://mlsanity.com/paper/2308.10527/) (2023)
- [UME: A Unified Meta-Generalization Framework for Cross-Domain ETA](https://mlsanity.com/paper/2606.00979/) (2026)
- [PRIME: Mitigating Subgroup Optimization Competition in Shared CTR Top Networks with Plug-in Residual Input-Conditioned Mixture of Expert](https://mlsanity.com/paper/2608.30449/) (2026)

## Abstract (arXiv)

In many web applications, deep learning-based CTR prediction models (deep CTR models for short) are widely adopted. Traditional deep CTR models learn patterns in a static manner, i.e., the network parameters are the same across all the instances. However, such a manner can hardly characterize each of the instances which may have different underlying distributions. It actually limits the representation power of deep CTR models, leading to sub-optimal results. In this paper, we propose an efficient, effective, and universal module, named as Adaptive Parameter Generation network (APG), which can dynamically generate parameters for deep CTR models on-the-fly based on different instances. Extensive experimental evaluation results show that APG can be applied to a variety of deep CTR models and significantly improve their performance. Meanwhile, APG can reduce the time cost by 38.7% and memory usage by 96.6% compared to a regular deep CTR model. We have deployed APG in the industrial sponsored search system and achieved 3% CTR gain and 1% RPM gain respectively.