DeepAI AI Chat
Log In Sign Up

Multi-Interest Network with Dynamic Routing for Recommendation at Tmall

04/17/2019
by   Chao Li, et al.
University of Technology Sydney
Alibaba Group
The Hong Kong University of Science and Technology
0

Industrial recommender systems usually consist of the matching stage and the ranking stage, in order to handle the billion-scale of users and items. The matching stage retrieves candidate items relevant to user interests, while the ranking stage sorts candidate items by user interests. Thus, the most critical ability is to model and represent user interests for either stage. Most of the existing deep learning-based models represent one user as a single vector which is insufficient to capture the varying nature of user's interests. In this paper, we approach this problem from a different view, to represent one user with multiple vectors encoding the different aspects of the user's interests. We propose the Multi-Interest Network with Dynamic routing (MIND) for dealing with user's diverse interests in the matching stage. Specifically, we design a multi-interest extractor layer based on capsule routing mechanism, which is applicable for clustering historical behaviors and extracting diverse interests. Furthermore, we develop a technique named label-aware attention to help learn a user representation with multiple vectors. 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 for recommendation. Currently, MIND has been deployed for handling major online traffic at the homepage on Mobile Tmall App.

READ FULL TEXT
03/23/2021

Diversity Regularized Interests Modeling for Recommender Systems

With the rapid development of E-commerce and the increase in the quantit...
05/18/2018

MARS: Memory Attention-Aware Recommender System

In this paper, we study the problem of modeling users' diverse interests...
07/14/2022

Improving Multi-Interest Network with Stable Learning

Modeling users' dynamic preferences from historical behaviors lies at th...
05/18/2021

Path-based Deep Network for Candidate Item Matching in Recommenders

The large-scale recommender system mainly consists of two stages: matchi...
02/18/2021

Multi-Interest-Aware User Modeling for Large-Scale Sequential Recommendations

Precise user modeling is critical for online personalized recommendation...
12/05/2021

Multiple Interest and Fine Granularity Network for User Modeling

User modeling plays a fundamental role in industrial recommender systems...
12/14/2019

Leveraging Multi-Method Evaluation for Multi-Stakeholder Settings

In this paper, we focus on recommendation settings with multiple stakeho...