Synergizing Implicit And Explicit User Interests: A Multi-embedding Retrieval Framework At Pinterest

Abstract

Industrial recommendation systems are typically composed of multiple stages, including retrieval, ranking, and blending. The retrieval stage plays a critical role in generating a high-recall set of candidate items that covers a wide range of diverse user interests. Effectively covering the diverse and long-tail user interests within this stage poses a significant challenge: traditional two-tower models struggle in this regard due to limited user-item feature interaction and often bias towards top use cases. To address these issues, we propose a novel multi-embedding retrieval framework designed to enhance user interest representation by generating multiple user embeddings conditioned on both implicit and explicit user interests. Implicit interests are captured from user history through a Differentiable Clustering Module (DCM), whereas explicit interests, such as topics that the user has followed, are modeled via Conditional Retrieval (CR). These methodologies represent a form of condit

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfan2025synergizing

Related papers

• Everyone's Preference Changes Differently: Weighted Multi-interest Retrieval Model (2022)0.00
• Rimirec: Modeling Refined Multi-interest In Hierarchical Structure For Recommendation (2024)0.00
• SPARC: Soft Probabilistic Adaptive Multi-interest Retrieval Model Via Codebooks For Recommender System (2025)0.00
• Knn-embed: Locally Smoothed Embedding Mixtures For Multi-interest Candidate Retrieval (2022)3.58
• SEMINAR: Search Enhanced Multi-modal Interest Network And Approximate Retrieval For Lifelong Sequential Recommendation (2024)0.00
• Bootstrapping Conditional Retrieval For User-to-item Recommendations (2025)4.52
• Embedding In Recommender Systems: A Survey (2023)0.00
• Decoupled Entity Representation Learning For Pinterest Ads Ranking (2025)0.00