MCNet: Monotonic Calibration Networks for Expressive Uncertainty Calibration in Online Advertising
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916636451143680 |
|---|---|
| author | Dai, Quanyu Xiao, Jiaren Du, Zhaocheng Zhu, Jieming Luo, Chengxiao Wu, Xiao-Ming Dong, Zhenhua |
| author_facet | Dai, Quanyu Xiao, Jiaren Du, Zhaocheng Zhu, Jieming Luo, Chengxiao Wu, Xiao-Ming Dong, Zhenhua |
| contents | In online advertising, uncertainty calibration aims to adjust a ranking model's probability predictions to better approximate the true likelihood of an event, e.g., a click or a conversion. However, existing calibration approaches may lack the ability to effectively model complex nonlinear relations, consider context features, and achieve balanced performance across different data subsets. To tackle these challenges, we introduce a novel model called Monotonic Calibration Networks, featuring three key designs: a monotonic calibration function (MCF), an order-preserving regularizer, and a field-balance regularizer. The nonlinear MCF is capable of naturally modeling and universally approximating the intricate relations between uncalibrated predictions and the posterior probabilities, thus being much more expressive than existing methods. MCF can also integrate context features using a flexible model architecture, thereby achieving context awareness. The order-preserving and field-balance regularizers promote the monotonic relationship between adjacent bins and the balanced calibration performance on data subsets, respectively. Experimental results on both public and industrial datasets demonstrate the superior performance of our method in generating well-calibrated probability predictions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00334 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MCNet: Monotonic Calibration Networks for Expressive Uncertainty Calibration in Online Advertising Dai, Quanyu Xiao, Jiaren Du, Zhaocheng Zhu, Jieming Luo, Chengxiao Wu, Xiao-Ming Dong, Zhenhua Machine Learning Artificial Intelligence H.0 In online advertising, uncertainty calibration aims to adjust a ranking model's probability predictions to better approximate the true likelihood of an event, e.g., a click or a conversion. However, existing calibration approaches may lack the ability to effectively model complex nonlinear relations, consider context features, and achieve balanced performance across different data subsets. To tackle these challenges, we introduce a novel model called Monotonic Calibration Networks, featuring three key designs: a monotonic calibration function (MCF), an order-preserving regularizer, and a field-balance regularizer. The nonlinear MCF is capable of naturally modeling and universally approximating the intricate relations between uncalibrated predictions and the posterior probabilities, thus being much more expressive than existing methods. MCF can also integrate context features using a flexible model architecture, thereby achieving context awareness. The order-preserving and field-balance regularizers promote the monotonic relationship between adjacent bins and the balanced calibration performance on data subsets, respectively. Experimental results on both public and industrial datasets demonstrate the superior performance of our method in generating well-calibrated probability predictions. |
| title | MCNet: Monotonic Calibration Networks for Expressive Uncertainty Calibration in Online Advertising |
| topic | Machine Learning Artificial Intelligence H.0 |
| url | https://arxiv.org/abs/2503.00334 |