FiBiNET: combining feature importance and bilinear feature interaction for click-through rate prediction

By Tongwen Huang, Zhiqi Zhang, Junlin Zhang. ACM Conference on Recommender Systems, 2019

372 citations recorded by the source corpus.

Advertising and feed ranking are essential to many Internet companies such as Facebook and Sina Weibo. Among many real-world advertising and feed ranking systems, click through rate (CTR) prediction plays a central role. There are many proposed models in this field such as logistic regression, tree based models, factorization machine based models and deep learning based CTR models. However, many current works calculate the feature interactions in a simple way such as Hadamard product and inner product and they care less about the importance of features. In this paper, a new model named FiBiNET as an abbreviation for Feature Importance and Bilinear feature Interaction NETwork is proposed to dynamically learn the feature importance and fine-grained feature interactions. On the one hand, the FiBiNET can dynamically learn the importance of features via the Squeeze-Excitation network (SENET) mechanism; on the other hand, it is able to effectively learn the feature interactions via bilinear function. We conduct extensive experiments on two real-world datasets and show that our shallow model outperforms other shallow models such as factorization machine(FM) and field-aware factorization machine(FFM). In order to improve performance further, we combine a classical deep neural network(DNN) component with the shallow model to be a deep model. The deep FiBiNET consistently outperforms the other state-of-the-art deep models such as DeepFM and extreme deep factorization machine(XdeepFM).

Subfields: Computer Vision and Pattern Recognition, Information Systems

View Paper: https://www.semanticscholar.org/paper/37908e8b2a6ff6d6592c9ee98afe824cf4100eaa

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Hai Jin
2. Kaigui Bian
3. Jongsoo Park
4. Yuanxing Zhang
5. Michael Tsang
6. Wei Yan
7. Dheevatsa Mudigere
8. Jiyan Yang

In Information Systems

1. Kaigui Bian
2. Jongsoo Park
3. Yuanxing Zhang
4. Wei Yan
5. Dheevatsa Mudigere
6. Jiyan Yang
7. Pengyu Zhao
8. Kecheng Xiao

Citations in the corpus

• Milvus: A Purpose-Built Vector Data Management System (2021, background): “Another source of multi-vector is that many applications use more than one machine learning model even for the same object to best describe that object [30, 69].”
• AMER: Automatic Behavior Modeling and Interaction Exploration in Recommender System (2020, methodology): “• FibiNet [31] employs SENET [29] to learn importance of embeddings, and then generates bilinear interactions on both SE and original feature embeddings as the input of MLP.”
• DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction (2022, background): “Since 2016, various deep models have been deployed by the business providers on their ads ranking services, such as Wide&Deep [6] on Google Play, DeepFM [11] on Huawei AppGallery, DIN [50] on Taobao, and FiBiNET on Weibo [15].”