Synergizing Implicit and Explicit User Interests: A Multi-Embedding Retrieval Framework at Pinterest

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fan, Zhibo, Lin, Hongtao, Chen, Haoyu, Deng, Bowen, Xia, Hedi, Yan, Yuke, Li, James
Format:	Preprint
Published:	2025
Subjects:	Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bootstrapping Conditional Retrieval for User-to-Item Recommendations
by: Lin, Hongtao, et al.
Published: (2025)

Retrieval Augmentation via User Interest Clustering
by: Lyu, Hanjia, et al.
Published: (2024)

User Long-Term Multi-Interest Retrieval Model for Recommendation
by: Meng, Yue, et al.
Published: (2025)

UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale
by: Li, Hanyu, et al.
Published: (2026)

Can One Embedding Fit All? A Multi-Interest Learning Paradigm Towards Improving User Interest Diversity Fairness
by: Zhao, Yuying, et al.
Published: (2024)

GemiRec: Interest Quantization and Generation for Multi-Interest Recommendation
by: Wu, Zhibo, et al.
Published: (2025)

Multi-Faceted Large Embedding Tables for Pinterest Ads Ranking
by: Su, Runze, et al.
Published: (2025)

Explicit and Implicit Semantic Ranking Framework
by: Zhu, Xiaofeng, et al.
Published: (2023)

TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterest
by: Xia, Xue, et al.
Published: (2023)

Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Prediction
by: Xu, Xiang, et al.
Published: (2024)

TransAct V2: Lifelong User Action Sequence Modeling on Pinterest Recommendation
by: Xia, Xue, et al.
Published: (2025)

Similar Users-Augmented Interest Network
by: Chen, Xiaolong, et al.
Published: (2026)

Improving feature interactions at Pinterest under industry constraints
by: Malreddy, Siddarth, et al.
Published: (2024)

Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models
by: Shi, Zhengliang, et al.
Published: (2025)

LLMs Meet Isolation Kernel: Lightweight, Learning-free Binary Embeddings for Fast Retrieval
by: Zhang, Zhibo, et al.
Published: (2026)

OmniSearchSage: Multi-Task Multi-Entity Embeddings for Pinterest Search
by: Agarwal, Prabhat, et al.
Published: (2024)

Interest Changes: Considering User Interest Life Cycle in Recommendation System
by: Cai, Yinjiang, et al.
Published: (2025)

Revisiting General Map Search via Generative Point-of-Interest Retrieval
by: Chen, Dong, et al.
Published: (2026)

Pyramid Mixer: Multi-dimensional Multi-period Interest Modeling for Sequential Recommendation
by: Gong, Zhen, et al.
Published: (2025)

MTMD: A Multi-Task Multi-Domain Framework for Unified Ad Lightweight Ranking at Pinterest
by: Yang, Xiao, et al.
Published: (2025)

Decoupled Multimodal Fusion for User Interest Modeling in Click-Through Rate Prediction
by: Fan, Alin, et al.
Published: (2025)

Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users
by: Li, Xiaodong, et al.
Published: (2026)

SIREN: Unified Multi-Granularity Semantic Interaction for Multi-Modal Lifelong User Interest Modeling
by: Zhang, Yaqian, et al.
Published: (2026)

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval
by: Hu, Ruofan, et al.
Published: (2025)

Treatment Effect Estimation for User Interest Exploration on Recommender Systems
by: Chen, Jiaju, et al.
Published: (2024)

DLF: Enhancing Explicit-Implicit Interaction via Dynamic Low-Order-Aware Fusion for CTR Prediction
by: Wang, Kefan, et al.
Published: (2025)

Unifying Multimodal Retrieval via Document Screenshot Embedding
by: Ma, Xueguang, et al.
Published: (2024)

MIM: Multi-modal Content Interest Modeling Paradigm for User Behavior Modeling
by: Yan, Bencheng, et al.
Published: (2025)

A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems
by: Zhou, Yichu, et al.
Published: (2026)

Diffusion Model for Interest Refinement in Multi-Interest Recommendation
by: Le, Yankun, et al.
Published: (2025)

SSEmb: A Joint Structural and Semantic Embedding Framework for Mathematical Formula Retrieval
by: Li, Ruyin, et al.
Published: (2025)

Multi-Interest Recommendation: A Survey
by: Li, Zihao, et al.
Published: (2025)

Embed Progressive Implicit Preference in Unified Space for Deep Collaborative Filtering
by: Zhang, Zhongjin, et al.
Published: (2025)

Temporal Interest Network for User Response Prediction
by: Zhou, Haolin, et al.
Published: (2023)

Improving Multi-modal Recommender Systems by Denoising and Aligning Multi-modal Content and User Feedback
by: Xv, Guipeng, et al.
Published: (2024)

Generative Chain of Behavior for User Trajectory Prediction
by: Huang, Chengkai, et al.
Published: (2026)

DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning
by: Yan, Yibo, et al.
Published: (2025)

Improving Pinterest Search Relevance Using Large Language Models
by: Wang, Han, et al.
Published: (2024)

User Invariant Preference Learning for Multi-Behavior Recommendation
by: Yan, Mingshi, et al.
Published: (2025)

MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMs
by: Huang, Jiani, et al.
Published: (2025)