Saved in:
Bibliographic Details
Main Authors: Lin, Chengzhi, Lin, Hezheng, Liu, Shuchang, Ruan, Cangguang, Xu, LingJing, Yang, Dezhao, Wang, Chuyuan, Liu, Yongqi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.03538
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909356258230272
author Lin, Chengzhi
Lin, Hezheng
Liu, Shuchang
Ruan, Cangguang
Xu, LingJing
Yang, Dezhao
Wang, Chuyuan
Liu, Yongqi
author_facet Lin, Chengzhi
Lin, Hezheng
Liu, Shuchang
Ruan, Cangguang
Xu, LingJing
Yang, Dezhao
Wang, Chuyuan
Liu, Yongqi
contents The proliferation of online micro-video platforms has underscored the necessity for advanced recommender systems to mitigate information overload and deliver tailored content. Despite advancements, accurately and promptly capturing dynamic user interests remains a formidable challenge. Inspired by the Platonic Representation Hypothesis, which posits that different data modalities converge towards a shared statistical model of reality, we introduce DreamUMM (Dreaming User Multi-Modal Representation), a novel approach leveraging user historical behaviors to create real-time user representation in a multimoda space. DreamUMM employs a closed-form solution correlating user video preferences with multimodal similarity, hypothesizing that user interests can be effectively represented in a unified multimodal space. Additionally, we propose Candidate-DreamUMM for scenarios lacking recent user behavior data, inferring interests from candidate videos alone. Extensive online A/B tests demonstrate significant improvements in user engagement metrics, including active days and play count. The successful deployment of DreamUMM in two micro-video platforms with hundreds of millions of daily active users, illustrates its practical efficacy and scalability in personalized micro-video content delivery. Our work contributes to the ongoing exploration of representational convergence by providing empirical evidence supporting the potential for user interest representations to reside in a multimodal space.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03538
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dreaming User Multimodal Representation Guided by The Platonic Representation Hypothesis for Micro-Video Recommendation
Lin, Chengzhi
Lin, Hezheng
Liu, Shuchang
Ruan, Cangguang
Xu, LingJing
Yang, Dezhao
Wang, Chuyuan
Liu, Yongqi
Information Retrieval
Artificial Intelligence
Computer Vision and Pattern Recognition
The proliferation of online micro-video platforms has underscored the necessity for advanced recommender systems to mitigate information overload and deliver tailored content. Despite advancements, accurately and promptly capturing dynamic user interests remains a formidable challenge. Inspired by the Platonic Representation Hypothesis, which posits that different data modalities converge towards a shared statistical model of reality, we introduce DreamUMM (Dreaming User Multi-Modal Representation), a novel approach leveraging user historical behaviors to create real-time user representation in a multimoda space. DreamUMM employs a closed-form solution correlating user video preferences with multimodal similarity, hypothesizing that user interests can be effectively represented in a unified multimodal space. Additionally, we propose Candidate-DreamUMM for scenarios lacking recent user behavior data, inferring interests from candidate videos alone. Extensive online A/B tests demonstrate significant improvements in user engagement metrics, including active days and play count. The successful deployment of DreamUMM in two micro-video platforms with hundreds of millions of daily active users, illustrates its practical efficacy and scalability in personalized micro-video content delivery. Our work contributes to the ongoing exploration of representational convergence by providing empirical evidence supporting the potential for user interest representations to reside in a multimodal space.
title Dreaming User Multimodal Representation Guided by The Platonic Representation Hypothesis for Micro-Video Recommendation
topic Information Retrieval
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.03538