# Everyone's Preference Changes Differently: Weighted Multi-Interest Retrieval Model

arXiv: https://arxiv.org/abs/2207.06652 · HTML: https://mlsanity.com/paper/2207.06652/

## 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 (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Neural Graph Collaborative Filtering](https://mlsanity.com/paper/1905.08108/) (2019)
- [Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation](https://mlsanity.com/paper/1609.09152/) (2016)
- [On the Turing Completeness of Modern Neural Network Architectures](https://mlsanity.com/paper/1901.03429/) (2019)
- [Multi-Interest Network with Dynamic Routing for Recommendation at Tmall](https://mlsanity.com/paper/1904.08030/) (2019)
- [Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba](https://mlsanity.com/paper/1803.02349/) (2018)
- [Controllable Multi-Interest Framework for Recommendation](https://mlsanity.com/paper/2005.09347/) (2020)
- [Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks](https://mlsanity.com/paper/1706.04148/) (2017)
- [PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest](https://mlsanity.com/paper/2007.03634/) (2020)
- [ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation](https://mlsanity.com/paper/1711.06632/) (2017)
- [Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems](https://mlsanity.com/paper/1904.04381/) (2019)
- [Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts](https://mlsanity.com/paper/1905.02138/) (2019)
- [Learning Bounded Context-Free-Grammar via LSTM and the Transformer:Difference and Explanations](https://mlsanity.com/paper/2112.09174/) (2021)

## Built on by (most cited first, 2 of 2)

- [MPFormer: Adaptive Framework for Industrial Multi-Task Personalized Sequential Retriever](https://mlsanity.com/paper/2508.20400/) (2025)
- [SPECTRA: Revealing the Full Spectrum of User Preferences via Distributional LLM Inference](https://mlsanity.com/paper/2509.24189/) (2025)

## 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.