InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate 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_ | 1866918139505147904 |
|---|---|
| author | Zeng, Zhichen Liu, Xiaolong Hang, Mengyue Liu, Xiaoyi Zhou, Qinghai Yang, Chaofei Liu, Yiqun Ruan, Yichen Chen, Laming Chen, Yuxin Hao, Yujia Xu, Jiaqi Nie, Jade Liu, Xi Zhang, Buyun Wen, Wei Yuan, Siyang Yin, Hang Zhang, Xin Wang, Kai Chen, Wen-Yen Han, Yiping Li, Huayu Yang, Chunzhi Long, Bo Yu, Philip S. Tong, Hanghang Yang, Jiyan |
| author_facet | Zeng, Zhichen Liu, Xiaolong Hang, Mengyue Liu, Xiaoyi Zhou, Qinghai Yang, Chaofei Liu, Yiqun Ruan, Yichen Chen, Laming Chen, Yuxin Hao, Yujia Xu, Jiaqi Nie, Jade Liu, Xi Zhang, Buyun Wen, Wei Yuan, Siyang Yin, Hang Zhang, Xin Wang, Kai Chen, Wen-Yen Han, Yiping Li, Huayu Yang, Chunzhi Long, Bo Yu, Philip S. Tong, Hanghang Yang, Jiyan |
| contents | Click-through rate (CTR) prediction, which predicts the probability of a user clicking an ad, is a fundamental task in recommender systems. The emergence of heterogeneous information, such as user profile and behavior sequences, depicts user interests from different aspects. A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction. However, most of the existing methods suffer from two fundamental limitations, including (1) insufficient inter-mode interaction due to the unidirectional information flow between modes, and (2) aggressive information aggregation caused by early summarization, resulting in excessive information loss. To address the above limitations, we propose a novel module named InterFormer to learn heterogeneous information interaction in an interleaving style. To achieve better interaction learning, InterFormer enables bidirectional information flow for mutually beneficial learning across different modes. To avoid aggressive information aggregation, we retain complete information in each data mode and use a separate bridging arch for effective information selection and summarization. Our proposed InterFormer achieves state-of-the-art performance on three public datasets and a large-scale industrial dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_09852 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction Zeng, Zhichen Liu, Xiaolong Hang, Mengyue Liu, Xiaoyi Zhou, Qinghai Yang, Chaofei Liu, Yiqun Ruan, Yichen Chen, Laming Chen, Yuxin Hao, Yujia Xu, Jiaqi Nie, Jade Liu, Xi Zhang, Buyun Wen, Wei Yuan, Siyang Yin, Hang Zhang, Xin Wang, Kai Chen, Wen-Yen Han, Yiping Li, Huayu Yang, Chunzhi Long, Bo Yu, Philip S. Tong, Hanghang Yang, Jiyan Information Retrieval Artificial Intelligence Machine Learning Click-through rate (CTR) prediction, which predicts the probability of a user clicking an ad, is a fundamental task in recommender systems. The emergence of heterogeneous information, such as user profile and behavior sequences, depicts user interests from different aspects. A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction. However, most of the existing methods suffer from two fundamental limitations, including (1) insufficient inter-mode interaction due to the unidirectional information flow between modes, and (2) aggressive information aggregation caused by early summarization, resulting in excessive information loss. To address the above limitations, we propose a novel module named InterFormer to learn heterogeneous information interaction in an interleaving style. To achieve better interaction learning, InterFormer enables bidirectional information flow for mutually beneficial learning across different modes. To avoid aggressive information aggregation, we retain complete information in each data mode and use a separate bridging arch for effective information selection and summarization. Our proposed InterFormer achieves state-of-the-art performance on three public datasets and a large-scale industrial dataset. |
| title | InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction |
| topic | Information Retrieval Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2411.09852 |