Wide & Deep Learning for Recommender Systems
ABSTRACT 通过特征的向量积（cross-product）对特征交叉的记忆具有可解释性，而泛化又需要更多的特征工程。而DNN通过对稀疏特征学习低维稠密的embedding表示对未出现的特征组合具有良好的泛化性能。但是，当用户物品关系比较稀疏，维度又比较高时，DNN容易过度泛化，推荐一些不相干的物品。文中提出Wide&Deep 学习，同时训练wide 部分和dnn，将记忆性和泛化性结合在一起。
相关文章
- 1. Wide & Deep Learning for Recommender Systems
- 2. Wide &Deep Learning for Recommender Systems
- 3. Wide & Deep Learning for Recommender Systems论文笔记
- 4. 《Wide & Deep Learning for Recommender Systems》论文总结
- 5. 论文笔记 - Wide & Deep Learning for Recommender Systems
- 6. #Paper Reading# Wide & Deep Learning for Recommender Systems
- 7. 论文阅读：《Wide & Deep Learning for Recommender Systems》
- 8. Wide & Deep Learning for Recommender Systems 翻译
- 9. 论文笔记：Wide & Deep Learning for Recommender Systems
- 10. Wide & Deep Learning for Recommender Systems 模型实践
- 更多相关文章...
- • Swift for 循环 - Swift 教程
- • Scala for循环 - Scala教程
- • Java Agent入门实战（三）-JVM Attach原理与使用
- • Java Agent入门实战（一）-Instrumentation介绍与使用
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. Wide & Deep Learning for Recommender Systems
- 2. Wide &Deep Learning for Recommender Systems
- 3. Wide & Deep Learning for Recommender Systems论文笔记
- 4. 《Wide & Deep Learning for Recommender Systems》论文总结
- 5. 论文笔记 - Wide & Deep Learning for Recommender Systems
- 6. #Paper Reading# Wide & Deep Learning for Recommender Systems
- 7. 论文阅读：《Wide & Deep Learning for Recommender Systems》
- 8. Wide & Deep Learning for Recommender Systems 翻译
- 9. 论文笔记：Wide & Deep Learning for Recommender Systems
- 10. Wide & Deep Learning for Recommender Systems 模型实践