IRA: Adaptive Interest-aware Representation and Alignment for Personalized Multi-interest Retrieval

2025-04-24

AI Summary

Online communities face challenges in personalized retrieval due to dynamic user interest evolution and the need for real-time adaptation to new content; existing methods rely heavily on click signals and struggle to jointly model temporal dynamics and semantic generalization. This paper proposes a cumulative Interest Unit (IU) mechanism that represents multi-interest contexts textually and supports temporal reinforcement/attenuation. We further design a purely semantic-driven retrieval alignment paradigm, eliminating dependence on click feedback and mitigating temporal bias. Our core innovations include unsupervised interest–document semantic alignment and click-free, fine-grained personalization modeling. Deployed at scale on the NAVER CAFE homepage, our approach yields a 12.7% lift in CTR in A/B tests, significantly improves long-tail interest coverage and cold-start document recall, and boosts diversity metrics by 23.5%.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Web Mining and Content Analysis: Community question answering

Abstract

Online community platforms require dynamic personalized retrieval and recommendation that can continuously adapt to evolving user interests and new documents. However, optimizing models to handle such changes in real-time remains a major challenge in large-scale industrial settings. To address this, we propose the Interest-aware Representation and Alignment (IRA) framework, an efficient and scalable approach that dynamically adapts to new interactions through a cumulative structure. IRA leverages two key mechanisms: (1) Interest Units that capture diverse user interests as contextual texts, while reinforcing or fading over time through cumulative updates, and (2) a retrieval process that measures the relevance between Interest Units and documents based solely on semantic relationships, eliminating dependence on click signals to mitigate temporal biases. By integrating cumulative Interest Unit updates with the retrieval process, IRA continuously adapts to evolving user preferences, ensuring robust and fine-grained personalization without being constrained by past training distributions. We validate the effectiveness of IRA through extensive experiments on real-world datasets, including its deployment in the Home Section of NAVER's CAFE, South Korea's leading community platform.

Problem

• Dynamic personalized retrieval for evolving user interests
• Real-time adaptation to new documents and interactions
• Mitigating temporal biases in personalized recommendation

Innovation

• Dynamic adaptation through cumulative Interest Units
• Semantic relevance without click signal dependency
• Continuous personalization via evolving user preferences