Deep Session Interest Network for Click-Through Rate Prediction

By Yufei Feng, Fuyu Lv, Weichen Shen, Menghan Wang, Fei Sun, Yu Zhu, Keping Yang. International Joint Conference on Artificial Intelligence, 2019

346 citations recorded by the source corpus.

Click-Through Rate (CTR) prediction plays an important role in many industrial applications, such as online advertising and recommender systems. How to capture users' dynamic and evolving interests from their behavior sequences remains a continuous research topic in the CTR prediction. However, most existing studies overlook the intrinsic structure of the sequences: the sequences are composed of sessions, where sessions are user behaviors separated by their occurring time. We observe that user behaviors are highly homogeneous in each session, and heterogeneous cross sessions. Based on this observation, we propose a novel CTR model named Deep Session Interest Network (DSIN) that leverages users' multiple historical sessions in their behavior sequences. We first use self-attention mechanism with bias encoding to extract users' interests in each session. Then we apply Bi-LSTM to model how users' interests evolve and interact among sessions. Finally, we employ the local activation unit to adaptively learn the influences of various session interests on the target item. Experiments are conducted on both advertising and production recommender datasets and DSIN outperforms other state-of-the-art models on both datasets.

Subfields: Computer Science Applications, Information Systems, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/419fe8b8edec6f849fecfd0d2bb11cacc4705180

How researchers see this paper

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

In Information Systems

1. Kaigui Bian
2. Xiaoqiang Zhu
3. Yuanxing Zhang
4. Kun Gai
5. Zhe Wang
6. Wei Yan
7. Qi Pi
8. Pengyu Zhao

Citations in the corpus

• Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction (2020, background): “Moreover, inspired by the success of the selfattention architecture in the tasks of sequence to sequence learning, Transformer is introduced in [3] to model user cross-session and in-session interest.”
• AMER: Automatic Behavior Modeling and Interaction Exploration in Recommender System (2020, methodology): “We randomly sampled 25% of the dataset, which remains 6,204,907 data instances [16].”