Multi-Interest Network with Dynamic Routing for Recommendation at Tmall

By C. Li, Zhiyuan Liu, Mengmeng Wu, Yuchi Xu, Pipei Huang, Huan Zhao, Guoliang Kang, Qiwei Chen, Dik Lun Lee. International Conference on Information and Knowledge Management, 2019

508 citations recorded by the source corpus.

Industrial recommender systems have embraced deep learning algorithms for building intelligent systems to make accurate recommendations. At its core, deep learning offers powerful ability for learning representations from data, especially for user and item representations. Existing deep learning-based models usually represent a user by one representation vector, which is usually insufficient to capture diverse interests for large-scale users in practice. In this paper, we approach the learning of user representations from a different view, by representing a user with multiple representation vectors encoding the different aspects of the user's interests. To this end, we propose the Multi-Interest Network with Dynamic routing (MIND) for learning user representations in recommender systems. Specifically, we design a multi-interest extractor layer based on the recently proposed dynamic routing mechanism, which is applicable for modeling and extracting diverse interests from user's behaviors. Furthermore, a technique named label-aware attention is proposed to help the learning process of user representations. Through extensive experiments on several public benchmarks and one large-scale industrial dataset from Tmall, we demonstrate that MIND can achieve superior performance than state-of-the-art methods in terms of recommendation accuracy. Currently, MIND has been deployed for handling major online traffic at the homepage on Mobile Tmall App.

Subfields: Artificial Intelligence, Computer Networks and Communications, Information Systems

View Paper: https://www.semanticscholar.org/paper/b56e5fb4f367a8d54614f1047bd4f9a2d58b9973

How researchers see this paper

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

In Artificial Intelligence

1. Jie Tang
2. Chang Zhou
3. Hongxia Yang
4. Fei Sun
5. Julian McAuley
6. Caiming Xiong
7. Jia Li
8. Bin Cui

In Computer Networks and Communications

1. Chang Zhou
2. Zhiwei Liu
3. Jie Tang
4. Jia Li
5. Caiming Xiong
6. Julian McAuley
7. Wei Li

In Information Systems

1. Fei Sun
2. Wenwu Ou
3. Jia Li
4. Bin Cui
5. Shiwen Wu
6. Zhiwei Liu
7. Fei Sun
8. Hongxia Yang

Citations in the corpus

• Intent Contrastive Learning for Sequential Recommendation (2022, background): “Recently, many approaches have been proposed to study users’ intents for improving recommendations [3, 17, 18, 41].”
• Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction (2020, background): “Capsule network and dynamic routing method are introduced in MIND to learn the representation of user interest as multiple vectors.”
• Graph Neural Networks in Recommender Systems: A Survey (2020, background): “, disentangled representation learning [105, 106] or capsule networks [82].”
• Controllable Multi-Interest Framework for Recommendation (2020, methodology): “The experimental result demonstrates that our ComiRec-SA and ComiRec-DR improve recall@50 by 1.39% and 8.65% compared with MIND, respectively.”
• Behavior sequence transformer for e-commerce recommendation in Alibaba (2019, background): “form in China, RSs have been the key engine for its Gross Merchandise Volume (GMV) and revenues, and various deep learning based recommendation methods have been deployed in rich e-commerce scenarios [1, 8, 10, 11, 14, 15, 17, 18]. As introduced in [15], the RSs in Alibaba are a two-stage pipeline: ”