Mitigate Position Bias with Coupled Ranking Bias on CTR Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916265092710400 |
|---|---|
| author | Zhao, Yao Liu, Zhining Cai, Tianchi Zhang, Haipeng Zhuang, Chenyi Gu, Jinjie |
| author_facet | Zhao, Yao Liu, Zhining Cai, Tianchi Zhang, Haipeng Zhuang, Chenyi Gu, Jinjie |
| contents | Position bias, i.e., users' preference of an item is affected by its placing position, is well studied in the recommender system literature. However, most existing methods ignore the widely coupled ranking bias, which is also related to the placing position of the item. Using both synthetic and industrial datasets, we first show how this widely coexisted ranking bias deteriorates the performance of the existing position bias estimation methods. To mitigate the position bias with the presence of the ranking bias, we propose a novel position bias estimation method, namely gradient interpolation, which fuses two estimation methods using a fusing weight. We further propose an adaptive method to automatically determine the optimal fusing weight. Extensive experiments on both synthetic and industrial datasets demonstrate the superior performance of the proposed methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_18971 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mitigate Position Bias with Coupled Ranking Bias on CTR Prediction Zhao, Yao Liu, Zhining Cai, Tianchi Zhang, Haipeng Zhuang, Chenyi Gu, Jinjie Information Retrieval Position bias, i.e., users' preference of an item is affected by its placing position, is well studied in the recommender system literature. However, most existing methods ignore the widely coupled ranking bias, which is also related to the placing position of the item. Using both synthetic and industrial datasets, we first show how this widely coexisted ranking bias deteriorates the performance of the existing position bias estimation methods. To mitigate the position bias with the presence of the ranking bias, we propose a novel position bias estimation method, namely gradient interpolation, which fuses two estimation methods using a fusing weight. We further propose an adaptive method to automatically determine the optimal fusing weight. Extensive experiments on both synthetic and industrial datasets demonstrate the superior performance of the proposed methods. |
| title | Mitigate Position Bias with Coupled Ranking Bias on CTR Prediction |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2405.18971 |