Feature Interaction based Neural Network for Click-Through Rate Prediction

Zou, Dafang; Zhang, Leiming; Mao, Jiafa; Sheng, Weiguo

doi:10.48550/arxiv.2006.05312

Cited by 1 publication

(2 citation statements)

References 34 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inner product, outer product and Hadamard product are commonly used interaction operations in CTR models. Some works [ 20 , 21 , 22 ] state that these operations are too simple to effectively model feature interactions and propose their own interaction operations to obtain a better expressive effect. A self-attention mechanism [ 11 ], which can be regarded as an interaction operation, has been utilized in CTR prediction models [ 23 , 24 , 25 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GAIN: A Gated Adaptive Feature Interaction Network for Click-Through Rate Prediction

Liu¹,

Ma²,

Wang³

2022

Sensors

View full text Add to dashboard Cite

CTR (Click-Through Rate) prediction has attracted more and more attention from academia and industry for its significant contribution to revenue. In the last decade, learning feature interactions have become a mainstream research direction, and dozens of feature interaction-based models have been proposed for the CTR prediction task. The most common approach for existing models is to enumerate all possible feature interactions or to learn higher-order feature interactions by designing complex models. However, a simple enumeration will introduce meaningless and harmful interactions, and a complex model structure will bring a higher complexity. In this work, we propose a lightweight, yet effective model called the Gated Adaptive feature Interaction Network (GAIN). We devise a novel cross module to drop meaningless feature interactions and preserve informative ones. Our cross module consists of multiple gated units, each of which can independently learn an arbitrary-order feature interaction. We combine the cross module with a deep module into GAIN and conduct comparative experiments with state-of-the-art models on two public datasets to verify its validity. Our experimental results show that GAIN can achieve a comparable or even better performance compared to its competitors. Furthermore, in order to verify the effectiveness of the feature interactions learned by GAIN, we transfer learned interactions to other models, such as Logistic Regression (LR) and Factorization Machines (FM), and find out that their performance can be significantly improved.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Integrated models usually consist of a shallow module and deep module. Some models [ 5 , 20 , 27 , 28 , 29 ] use a single-tower architecture, in which two modules work in sequence, while other models [ 3 , 17 , 30 , 31 , 32 ] choose a dual-tower architecture, in which two modules work in parallel. Chen et al.…”

Section: Introductionmentioning

confidence: 99%