Research on Short-Video Platform User Decision-Making via Multimodal Temporal Modeling and Reinforcement Learning
On the map: Deep reinforcement learning methods → Deep RL algorithms and representations
Abstract (arXiv)
This paper proposes the MT-DQN model, which integrates a Transformer, Temporal Graph Neural Network (TGNN), and Deep Q-Network (DQN) to address the challenges of predicting user behavior and optimizing recommendation strategies in short-video environments. Experiments demonstrated that MT-DQN consistently outperforms traditional concatenated models, such as Concat-Modal, achieving an average F1-score improvement of 10.97% and an average NDCG@5 improvement of 8.3%. Compared to the classic reinforcement learning model Vanilla-DQN, MT-DQN reduces MSE by 34.8% and MAE by 26.5%. Nonetheless, we also recognize challenges in deploying MT-DQN in real-world scenarios, such as its computational cost and latency sensitivity during online inference, which will be addressed through future architectural optimization.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 38 of its 112 references that are in the map. First posted on arXiv 13 Sep 2025.
Builds on
38 of 112 references.
Closest ancestors · 1
Same direction, newest first
Other references · 37
- 2016YouTube-8M: A Large-Scale Video Classification Benchmarkcited by 324
- 2021Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Taskscited by 78
- 2022Transformer-based Multimodal Information Fusion for Facial Expression Analysiscited by 49
- 2021Multimodal Engagement Analysis from Facial Videos in the Classroomcited by 27
- 2024Deep Learning-based Anomaly Detection and Log Analysis for Computer Networkscited by 23
- 2024Automatic News Generation and Fact-Checking System Based on Language Processingcited by 22
- 2022Multi-Behavior Sequential Recommendation with Temporal Graph Transformercited by 20
- 2024Image anomaly detection and prediction scheme based on SSA optimized ResNet50-BiGRU modelcited by 18
- 2024Enhancing Visual Question Answering through Ranking-Based Hybrid Training and Multimodal Fusioncited by 16
- 2024The Design of Autonomous UAV Prototypes for Inspecting Tunnel Construction Environmentcited by 15
- 2023User Retention-oriented Recommendation with Decision Transformercited by 14
- 2025Trajectory Prediction Meets Large Language Models: A Surveycited by 14
25 more
- 2024Cross-border Commodity Pricing Strategy Optimization via Mixed Neural Network for Time Series Analysiscited by 12
- 2020Weibo-COV: A Large-Scale COVID-19 Social Media Dataset from Weibocited by 11
- 2024Deep Analysis of Time Series Data for Smart Grid Startup Strategies: A Transformer-LSTM-PSO Model Approachcited by 11
- 2024Recording Brain Activity While Listening to Music Using Wearable EEG Devices Combined with Bidirectional Long Short-Term Memory Networkscited by 8
- 2024EITNet: An IoT-Enhanced Framework for Real-Time Basketball Action Recognitioncited by 8
- 2024Real-time Monitoring of Lower Limb Movement Resistance Based on Deep Learningcited by 8
- 2024LTPNet Integration of Deep Learning and Environmental Decision Support Systems for Renewable Energy Demand Forecastingcited by 7
- 2024Real-time Monitoring and Analysis of Track and Field Athletes Based on Edge Computing and Deep Reinforcement Learning Algorithmcited by 7
- 2024IoT-Based 3D Pose Estimation and Motion Optimization for Athletes: Application of C3D and OpenPosecited by 7
- 2024TRIZ Method for Urban Building Energy Optimization: GWO-SARIMA-LSTM Forecasting modelcited by 6
- 2024GTA-Net: An IoT-Integrated 3D Human Pose Estimation System for Real-Time Adolescent Sports Posture Correctioncited by 5
- 2024Optimized CNNs for Rapid 3D Point Cloud Object Recognitioncited by 5
- 2024Electronic Health Records-Based Data-Driven Diabetes Knowledge Unveiling and Risk Prognosiscited by 5
- 2024Temporal-Aware Evaluation and Learning for Temporal Graph Neural Networkscited by 5
- 2024PLoc: A New Evaluation Criterion Based on Physical Location for Autonomous Driving Datasetscited by 4
- 2025Unsupervised Search for Ethnic Minorities' Medical Segmentation Training Setcited by 4
- 2025Intelligent logistics management robot path planning algorithm integrating transformer and GCN networkcited by 4
- 2019Dynamic Multi-path Neural Networkcited by 3
- 2025Impact of Short-Duration Aerobic Exercise Intensity on Executive Function and Sleepcited by 3
- 2025The effect of intelligent monitoring of physical exercise on executive function in children with ADHDcited by 3
- 2025CPLOYO: A Pulmonary Nodule Detection Model with Multi-Scale Feature Fusion and Nonlinear Feature Learningcited by 3
- 2025MamNet: A Novel Hybrid Model for Time-Series Forecasting and Frequency Pattern Analysis in Network Trafficcited by 3
- 2022Constrained Reinforcement Learning for Short Video Recommendationcited by 2
- 2024Allo-AVA: A Large-Scale Multimodal Conversational AI Dataset for Allocentric Avatar Gesture Animationcited by 2
- 2025Reinforcement Learning in Strategy-Based and Atari Games: A Review of Google DeepMinds Innovationscited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Breaking the Cold-Start Barrier: Reinforcement Learning with Double and Dueling DQNs
- 2024A Model-based Multi-Agent Personalized Short-Video Recommender System
- 2025Predicting E-commerce Purchase Behavior using a DQN-Inspired Deep Learning Model for enhanced adaptability
- 2025DMGIN: How Multimodal LLMs Enhance Large Recommendation Models for Lifelong User Post-click Behaviors
- 2026Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation
- 2026NEXT: Reasoning-Driven Video Recommendation via a Vision-Language Model
- 2024Transforming Game Play: A Comparative Study of DCQN and DTQN Architectures in Reinforcement Learning
- 2025VRAgent-R1: Boosting Video Recommendation with MLLM-based Agents via Reinforcement Learning