Optimizing Recall Or Relevance? A Multi-task Multi-head Approach For Item-to-item Retrieval In Recommendation

Abstract

The task of item-to-item (I2I) retrieval is to identify a set of relevant and highly engaging items based on a given trigger item. It is a crucial component in modern recommendation systems, where users' previously engaged items serve as trigger items to retrieve relevant content for future engagement. However, existing I2I retrieval models in industry are primarily built on co-engagement data and optimized using the recall measure, which overly emphasizes co-engagement patterns while failing to capture semantic relevance. This often leads to overfitting short-term co-engagement trends at the expense of long-term benefits such as discovering novel interests and promoting content diversity. To address this challenge, we propose MTMH, a Multi-Task and Multi-Head I2I retrieval model that achieves both high recall and semantic relevance. Our model consists of two key components: 1) a multi-task learning loss for formally optimizing the trade-off between recall and semantic relevance, and 2

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2025optimizing

Related papers

• SEMINAR: Search Enhanced Multi-modal Interest Network And Approximate Retrieval For Lifelong Sequential Recommendation (2024)0.00
• PI2I: A Personalized Item-based Collaborative Filtering Retrieval Framework (2026)0.00
• Revisiting Neural Retrieval On Accelerators (2023)9.41
• Everyone's Preference Changes Differently: Weighted Multi-interest Retrieval Model (2022)0.00
• Self-supervised Multi-modal Sequential Recommendation (2023)0.00
• Synergizing Implicit And Explicit User Interests: A Multi-embedding Retrieval Framework At Pinterest (2025)0.00
• Task-adaptive Retrieval Over Agentic Multi-modal Web Histories Via Learned Graph Memory (2026)0.00
• DS@GT At TREC TOT 2025: Bridging Vague Recollection With Fusion Retrieval And Learned Reranking (2026)0.00