推荐算法从传统方法到深度学习方法发展里程碑
| 时间 | 作者 | 技术名称 | 说明 |
|---|---|---|---|
| 2003 | Amazon | ItemCF(基于物品的协同过滤) | 不仅让Amazon的推荐系统广为人知，更让协同过滤成为今后很长时间的研究热点和业界主流的推荐模型。 |
| 2006 | Netflix | MF(矩阵分解) | 在Netflix Prize Challenge中，以矩阵分解为主的推荐算法大放异彩，拉开了矩阵分解在业界流行的序幕。 |
| LR(逻辑回归) | 深度学习的基础性结构，能够融合多特征，成为了独立于协同过滤的推荐模型的另一个重要发展方向 | ||
| 2010 | Rendle | FM | FM在2012~2014年前后，成为业界主流的推荐模型之一 |
| 2015 | Yuchi Juan | FFM | 基于FM提出的FFM在多项CRT预估大赛中夺魁，并被Criteo、美团等公司深度应用在推荐系统、CTR预估等领域 |
| 2014 | GBDT+LR | 利用GBDT自动进行特征筛选和组合，解决了工程上应用LR的特征组合难度。 | |
| 2017 | 阿里巴巴 | LS-PLM | 自动2012年起成为阿里巴巴主流推荐模型，直至2017年才公开，与三层神经网络及其相似，可以把它看成连接前后深度学习时代的节点。 |
| 2015 | 澳大利亚国立大学 | AutoRec | 将自编码器的思想与协同过滤结合，提出了一种单隐层神经网络推荐模型 |
| 2016 | 微软 | Deep Crossing | 深度学习架构在推荐系统中的完整应用 |
| 2016 | 谷歌 | Wide&Deep | 自提出至今一直在业界发挥着巨大影响力的模型，Wide部分具有逻辑回归的优点，Deep部分具有深度神经网络的优点。 |
| 2018 | 阿里巴巴 | DIN | 是一次基于实际业务观察的模型改进，提了业界非常知名的深度兴趣网络，把注意力机制引入深度学习推荐模型，用于捕捉用户兴趣。 |
| 2019 | 阿里巴巴 | DIEN | 兴趣进化网络，DIN的演化版本，引入序列模型，用于模拟用户兴趣进化过程。 |
本文永久更新地址: https://notlate.cn/p/9e23100d848390f4/
Your point of view caught my eye and was very interesting. Thanks. I have a question for you.
Your article helped me a lot, is there any more related content? Thanks! https://www.binance.com/en-IN/register?ref=UM6SMJM3
Thanks for sharing. I read many of your blog posts, cool, your blog is very good.
Thanks for sharing. I read many of your blog posts, cool, your blog is very good.
I don’t think the title of your article matches the content lol. Just kidding, mainly because I had some doubts after reading the article.
Your article helped me a lot, is there any more related content? Thanks!
Can you be more specific about the content of your article? After reading it, I still have some doubts. Hope you can help me.
Your point of view caught my eye and was very interesting. Thanks. I have a question for you.
I don’t think the title of your article matches the content lol. Just kidding, mainly because I had some doubts after reading the article.
Thank you for your sharing. I am worried that I lack creative ideas. It is your article that makes me full of hope. Thank you. But, I have a question, can you help me?
I don’t think the title of your article matches the content lol. Just kidding, mainly because I had some doubts after reading the article.