Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising

By Junwei Pan, Jian Xu, Alfonso Lobos Ruiz, Wenliang Zhao, Shengjun Pan, Yu Sun, Quan Lu. 2018

245 citations recorded by the source corpus.

Click-through rate (CTR) prediction is a critical task in online display advertising. The data involved in CTR prediction are typically multi-field categorical data, i.e., every feature is categorical and belongs to one and only one field. One of the interesting characteristics of such data is that features from one field often interact differently with features from different other fields. Recently, Field-aware Factorization Machines (FFMs) have been among the best performing models for CTR prediction by explicitly modeling such difference. However, the number of parameters in FFMs is in the order of feature number times field number, which is unacceptable in the real-world production systems. In this paper, we propose Field-weighted Factorization Machines (FwFMs) to model the different feature interactions between different fields in a much more memory-efficient way. Our experimental evaluations show that FwFMs can achieve competitive prediction performance with only as few as 4% parameters of FFMs. When using the same number of parameters, FwFMs can bring 0.92% and 0.47% AUC lift over FFMs on two real CTR prediction data sets.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Information Systems

How researchers see this paper

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

In Computer Networks and Communications

1. Yupeng Hou
2. Ji-rong Wen
3. Jiliang Tang
4. Yong Yu
5. Weinan Zhang
6. Wayne Xin Zhao
7. Xiangyu Zhao
8. Haibo Wang

In Computer Vision and Pattern Recognition

1. Zhenguo Li
2. Ji-rong Wen
3. Jiliang Tang
4. Weinan Zhang
5. Yong Yu
6. Xiuqiang He
7. Wayne Xin Zhao
8. Stefanos P. Zafeiriou

In Information Systems

1. Wayne Xin Zhao
2. Yupeng Hou
3. Ji-rong Wen
4. Zhenguo Li
5. Ruiming Tang
6. Weinan Zhang
7. Xiuqiang He
8. Yong Yu

Citations in the corpus

• AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations (2020, background): “Compared to hand-crafted features, well-learned embeddings have been demonstrated to significantly enhance the recommendation performance [5, 8, 21, 24, 38].”
• RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms (2020, background): “Context-aware recommendation LR DIN Zhou et al. (2018) DSSM Huang et al.”
• AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction (2020, methodology): “] models to show its effectiveness (denoted asAutoFM and AutoDeepFM, respectively). We compare it with GBDTbased methods (GBDT+LR [11], GBDT+FFM [15]) and Factorization Machine models (AFM [30], FwFM [23], FFM [14], IPNN [25]). Due to its huge computational costs and the unavailability of the source”
• AutoGroup: Automatic Feature Grouping for Modelling Explicit High-Order Feature Interactions in CTR Prediction (2020, methodology): “For sparse data, Factorization Machine (FM) and its variants [24, 29] project each feature into a low-dimensional vector and models feature interactions by inner product while FFM [14] enables each feature to have multiple latent vectors to interact with features from different”