Sequential Scenario-Specific Meta Learner for Online Recommendation简析
Sequential Scenario-Specific Meta Learner for Online Recommendation Introduction 冷启动是个长期存在的挑战对于通常的推荐场景来讲。大多数推荐算法依赖于大量的观察数据，以及对于没什么联系的推荐算法产生不了足够好的效果。为了解决这个问题，文章使用了few-shot learning以及meta learning,提出了
相关文章
- 1. [paper] Meta-Learner LSTM
- 2. Memory Augmented Graph Neural Networks for Sequential Recommendation翻译
- 3. A SIMPLE NEURAL ATTENTIVE META-LEARNER
- 4. Sequential Recommendation with User Memory Networks简介
- 5. 联邦学习论文阅读：Federated meta-learning for recommendation
- 6. DKN: Deep Knowledge-Aware Network for News Recommendation简析
- 7. NAIS: Neural Attentive Item Similarity Model for Recommendation简析
- 8. Online Meta-Learning
- 9. Controllable Multi-Interest Framework for Recommendation
- 10. 序列推荐模型梳理（Sequential Recommendation）
- 更多相关文章...
- • Swift for 循环 - Swift 教程
- • Scala for循环 - Scala教程
- • Github 简明教程
- • Git可视化极简易教程 — Git GUI使用方法
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. [paper] Meta-Learner LSTM
- 2. Memory Augmented Graph Neural Networks for Sequential Recommendation翻译
- 3. A SIMPLE NEURAL ATTENTIVE META-LEARNER
- 4. Sequential Recommendation with User Memory Networks简介
- 5. 联邦学习论文阅读：Federated meta-learning for recommendation
- 6. DKN: Deep Knowledge-Aware Network for News Recommendation简析
- 7. NAIS: Neural Attentive Item Similarity Model for Recommendation简析
- 8. Online Meta-Learning
- 9. Controllable Multi-Interest Framework for Recommendation
- 10. 序列推荐模型梳理（Sequential Recommendation）