Optimizing Recall or Relevance? A Multi-Task Multi-Head Approach for Item-to-Item Retrieval in Recommendation

2025-06-06

AI Summary

Existing item-to-item (I2I) retrieval models over-rely on co-click behavioral data, leading to insufficient semantic relevance modeling, weak discovery of long-tail interests, and degraded recommendation diversity. To address these limitations, we propose a multi-task, multi-head I2I retrieval framework—the first to jointly optimize recall and semantic relevance. Our approach employs a shared encoder with multiple task-specific output heads to simultaneously capture short-term behavioral patterns and long-term semantic associations. A novel joint loss function integrates large-scale co-interaction data (billions of instances) with fine-grained semantic annotations for end-to-end training. Evaluated on an industrial-scale platform, our method achieves a 14.4% improvement in recall and a 56.6% gain in semantic relevance, while significantly enhancing long-tail item coverage and user long-term satisfaction.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Learning Preferences or Rankings
• Computer Vision: Image and Video Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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) a multi-head I2I retrieval architecture for retrieving both highly co-engaged and semantically relevant items. We evaluate MTMH using proprietary data from a commercial platform serving billions of users and demonstrate that it can improve recall by up to 14.4% and semantic relevance by up to 56.6% compared with prior state-of-the-art models. We also conduct live experiments to verify that MTMH can enhance both short-term consumption metrics and long-term user-experience-related metrics. Our work provides a principled approach for jointly optimizing I2I recall and semantic relevance, which has significant implications for improving the overall performance of recommendation systems.

Problem

• Balancing recall and semantic relevance in item-to-item retrieval
• Overcoming overfitting to short-term co-engagement trends
• Improving both short-term and long-term recommendation performance

Innovation

• Multi-task learning optimizes recall and relevance
• Multi-head architecture retrieves diverse item types
• Balances short-term engagement and long-term benefits