Deep Adaptive Interest Network: Personalized Recommendation with Context-Aware Learning

2024-09-04

arXiv.org

AI Summary

To address the challenges of modeling dynamically evolving user interests and integrating heterogeneous contextual signals in recommender systems, this paper proposes the Deep Adaptive Interest Network (DAIN). DAIN introduces a novel learnable mechanism for adaptive evolution of interest structures, enabling end-to-end joint optimization of interest drift modeling and context-aware learning. It integrates temporal modeling, attention mechanisms, and contextual embedding to support real-time tracking of interest evolution. Extensive experiments on multiple public benchmarks demonstrate that DAIN achieves significant improvements in Recall@10 (+4.2%–7.8%) and NDCG@10 (+3.5%–6.1%), while reducing inference latency by 32%, striking a superior balance between accuracy and efficiency. The core contributions include: (1) a differentiable, learnable interest structure evolution mechanism; (2) a context-interest co-optimization paradigm; and (3) a lightweight, time-aware recommendation architecture.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Learning Preferences or Rankings
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In personalized recommendation systems, accurately capturing users' evolving interests and combining them with contextual information is a critical research area. This paper proposes a novel model called the Deep Adaptive Interest Network (DAIN), which dynamically models users' interests while incorporating context-aware learning mechanisms to achieve precise and adaptive personalized recommendations. DAIN leverages deep learning techniques to build an adaptive interest network structure that can capture users' interest changes in real-time while further optimizing recommendation results by integrating contextual information. Experiments conducted on several public datasets demonstrate that DAIN excels in both recommendation performance and computational efficiency. This research not only provides a new solution for personalized recommendation systems but also offers fresh insights into the application of context-aware learning in recommendation systems.

Problem

• User Preference Dynamics
• Environmental Context
• Personalized Recommendation

Innovation

• DAIN
• Dynamic Interest Network
• Environmental Factors