mlsanityData to 14 Oct 2026

Reinforcing User Interest Evolution in Multi-Scenario Learning for recommender systems

arXiv 2506.17682 ↗First posted 21 Jun 2025cs.IR cs.AIcited by 0

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

In real-world recommendation systems, users would engage in variety scenarios, such as homepages, search pages, and related recommendation pages. Each of these scenarios would reflect different aspects users focus on. However, the user interests may be inconsistent in different scenarios, due to differences in decision-making processes and preference expression. This variability complicates unified modeling, making multi-scenario learning a significant challenge. To address this, we propose a novel reinforcement learning approach that models user preferences across scenarios by modeling user interest evolution across multiple scenarios. Our method employs Double Q-learning to enhance next-item prediction accuracy and optimizes contrastive learning loss using Q-value to make model performance better. Experimental results demonstrate that our approach surpasses state-of-the-art methods in multi-scenario recommendation tasks. Our work offers a fresh perspective on multi-scenario modeling and highlights promising directions for future research.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 14 of its 19 references that are in the map. First posted on arXiv 21 Jun 2025.

Builds on

14 of 19 references.

References · 14

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  5. 2018Self-Attentive Sequential Recommendationcited by 1,184
  6. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
  7. 2016Wide & Deep Learning for Recommender Systemscited by 747
  8. 2017Deep Interest Network for Click-Through Rate Predictioncited by 544
  9. 2018Personalized Top-N Sequential Recommendation via Convolutional Sequence Embeddingcited by 476
  10. 2017Deep & Cross Network for Ad Click Predictionscited by 393
  11. 2018Top-K Off-Policy Correction for a REINFORCE Recommender Systemcited by 182
  12. 2018A Simple Convolutional Generative Network for Next Item Recommendationcited by 120
2 more
  1. 2021One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Predictioncited by 78
  2. 2023PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Informationcited by 60

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-Enhanced Reinforcement Learning for Long-Term User Satisfaction in Interactive Recommendation
  2. 2024Multi-Scenario Combination Based on Multi-Agent Reinforcement Learning to Optimize the Advertising Recommendation System
  3. 2024UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender Systems
  4. 2020Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation
  5. 2025PERSCEN: Learning Personalized Interaction Pattern and Scenario Preference for Multi-Scenario Matching
  6. 2023Robust Reinforcement Learning Objectives for Sequential Recommender Systems
  7. 2021Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation
  8. 2023On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems