Everyone's Preference Changes Differently: Weighted Multi-Interest Retrieval Model
Not on the map. Why?
Abstract (arXiv)
User embeddings (vectorized representations of a user) are essential in recommendation systems. Numerous approaches have been proposed to construct a representation for the user in order to find similar items for retrieval tasks, and they have been proven effective in industrial recommendation systems as well. Recently people have discovered the power of using multiple embeddings to represent a user, with the hope that each embedding represents the user's interest in a certain topic. With multi-interest representation, it's important to model the user's preference over the different topics and how the preference change with time. However, existing approaches either fail to estimate the user's affinity to each interest or unreasonably assume every interest of every user fades with an equal rate with time, thus hurting the recall of candidate retrieval. In this paper, we propose the Multi-Interest Preference (MIP) model, an approach that not only produces multi-interest for users by using the user's sequential engagement more effectively but also automatically learns a set of weights to represent the preference over each embedding so that the candidates can be retrieved from each interest proportionally. Extensive experiments have been done on various industrial-scale datasets to demonstrate the effectiveness of our approach.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 42 references that are in the map. First posted on arXiv 14 Jul 2022.
Builds on
18 of 42 references.
References · 18
- 2017Attention Is All You Needcited by 60,361
- 2018Self-Attentive Sequential Recommendationcited by 1,184
- 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
- 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
- 2016Wide & Deep Learning for Recommender Systemscited by 747
- 2017Dynamic Routing Between Capsulescited by 689
- 2019Neural Graph Collaborative Filteringcited by 661
- 2016Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendationcited by 152
- 2019On the Turing Completeness of Modern Neural Network Architecturescited by 129
- 2019Multi-Interest Network with Dynamic Routing for Recommendation at Tmallcited by 114
- 2018Billion-scale Commodity Embedding for E-commerce Recommendation in Alibabacited by 105
- 2020Controllable Multi-Interest Framework for Recommendationcited by 93
6 more
- 2017Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networkscited by 84
- 2020PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterestcited by 75
- 2017ATRank: An Attention-Based User Behavior Modeling Framework for Recommendationcited by 45
- 2019Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systemscited by 28
- 2019Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contextscited by 19
- 2021Learning Bounded Context-Free-Grammar via LSTM and the Transformer:Difference and Explanationscited by 7
Built on by
Citing papers per year: 2025: 2.
2 papers.