用多模态时序建模提升短视频推荐精准度
Research on Short-Video Platform User Decision-Making via Multimodal Temporal Modeling and Reinforcement Learning
- 融合Transformer与图网络，捕捉用户行为时序特征
- 相比基线模型，F1提升10.97%，推荐准确率显著提高
- 适合需要高精度推荐的平台研发人员参考
本文提出MT-DQN模型，整合Transformer、时序图神经网络（TGNN）与深度Q网络（DQN），解决短视频场景下用户行为预测与推荐策略优化难题。实验表明，MT-DQN持续优于传统拼接模型（如Concat-Modal），平均F1-score提升10.97%，平均NDCG@5提升8.3%；相较于经典强化学习模型Vanilla-DQN，MT-DQN将均方误差（MSE）降低34.8%，平均绝对误差（MAE）减少26.5%。然而，该模型在真实场景部署中仍面临计算开销大、在线推理延迟敏感等挑战，未来将通过架构优化加以解决。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。