Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
推荐/广告/搜索领域工业界经典以及最前沿论文集合。A collection of industry classics and cutting-edge papers in the field of recommendation/advertising/search.
| Date | Stars |
|---|---|
| 2026-07-24 | 2168 |
| 2026-07-25 | 2168 |
| 2026-07-28 | 2174 |
| 2026-07-30 | 2174 |
| 2026-08-06 | 2174 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# 推荐系统相关论文汇总
([English Version is Here](/README_EN.md))
## 介绍
1. 截至2026-06-11，本仓库收集汇总了推荐系统领域相关论文共**948**篇，涉及：**召回**，**粗排**，**精排**，**重排**，**多任务**，**多场景**，**多模态**，**冷启动**，**校准**，
**纠偏**，**多样性**，**公平性**，**反馈延迟**，**蒸馏**，**对比学习**，**因果推断**，**Look-Alike**，**Learning-to-Rank**，**强化学习**等领域，本仓库会跟踪业界进展，持续更新。
2. 因文件名特殊字符的限制，故论文title中所有的`:`都改为了`-`，检索时请注意。
3. 文件名前缀中带有`[]`的，表明本人已经通读过，第一个`[]`中为论文年份，第二个`[]`中为发表机构或公司(可选)，第三个`[]`中为论文提出的model或method的简称(可选)。
4. 在某些一级分类下面，还有若干二级分类；一篇论文可能应该涉及多个二级分类(例如用对比学习的方法做召回)，最终我会将论文放在较主要的那一类下；分类也会随时调整优化，欢迎在`issue`中提出宝贵意见。
5. 若您是文章作者，且不希望您的论文出现在这里，请在`issue`中提出，我核实后会马上下架。
6. 关于排序算法的一些实现，请见我的另一个repo: https://github.com/tangxyw/RecAlgorithm
7. 本仓库仅供交流学习使用，不做任何商业目的。
## 联系方式
<img src='Wechat.jpeg' alt='pic' width='220' height='220'>
## 论文目录
- [Rank](#Rank)
- [Industry](#Industry)
- [Pre-Rank](#Pre-Rank)
- [Re-Rank](#Re-Rank)
- [Match](#Match)
- [Multi-Task](#Multi-Task)
- [Multi-Modal](#Multi-Modal)
- [Multi-Scenario](#Multi-Scenario)
- [Debias](#Debias)
- [Calibration](#Calibration)
- [Distillation](#Distillation)
- [Feedback-Delay](#Feedback-Delay)
- [ContrastiveLearning](#ContrastiveLearning)
- [Cold-Start](#Cold-Start)
- [Learning-to-Rank](#Learning-to-Rank)
- [Fairness](#Fairness)
- [Look-Alike](#Look-Alike)
- [CausalInference](#CausalInference)
- [Diversity](#Diversity)
- [ABTest](#ABTest)
- [ReinforcementLearning](#ReinforcementLearning)
## Rank
- [[2009][BPR] Bayesian Personalized Ranking from Implicit Feedback](Rank/%5B2009%5D%5BBPR%5D%20Bayesian%20Personalized%20Ranking%20from%20Implicit%20Feedback.pdf)
- [[2010][FM] Factorization Machines](Rank/%5B2010%5D%5BFM%5D%20Factorization%20Machines.pdf)
- [[2014][Facebook][GBDT+LR] Practical Lessons from Predicting Clicks on Ads at Facebook](Rank/%5B2014%5D%5BFacebook%5D%5BGBDT%2BLR%5D%20Practical%20Lessons%20from%20Predicting%20Clicks%20on%20Ads%20at%20Facebook.pdf)
- [[2016][UCL][FNN] Deep Learning over Multi-field Categorical Data](Rank/%5B2016%5D%5BUCL%5D%5BFNN%5D%20Deep%20Learning%20over%20Multi-field%20Categorical%20Data.pdf)
- [[2016][Microsft][Deep Crossing] Deep Crossing - Web-Scale Modeling without Manually Crafted Combinatorial Features](Rank/%5B2016%5D%5BMicrosft%5D%5BDeep%20Crossing%5D%20Deep%20Crossing%20-%20Web-Scale%20Modeling%20without%20Manually%20Crafted%20Combinatorial%20Features.pdf)
- [[2016][Google][Wide&Deep] Wide & Deep Learning for Recommender Systems](Rank/%5B2016%5D%5BGoogle%5D%5BWide%26Deep%5D%20Wide%20%26%20Deep%20Learning%20for%20Recommender%20Systems.pdf)
- [[2016][SJTU][PNN] Product-based Neural Networks for User Response Prediction](Rank/%5B2016%5D%5BSJTU%5D%5BPNN%5D%20Product-based%20Neural%20Networks%20for%20User%20Response%20Prediction.pdf)
- [[2016][NTU][FFM] Field-aware Factorization Machines for CTR Prediction](Rank/%5B2016%5D%5BNTU%5D%5BFFM%5D%20Field-aware%20Factorization%20Machines%20for%20CTR%20Prediction.pdf)
- [[2017][Stanford][DCN] Deep & Cross Network for Ad Click Predictions](Rank/%5B2017%5D%5BStanford%5D%5BDCN%5D%20Deep%20%26%20Cross%20Network%20for%20Ad%20Click%20Predictions.pdf)
- [[2017][NUS][NFM] Neural Factorization Machines for Sparse Predictive Analytics](Rank/%5B2017%5D%5BNUS%5D%5BNFM%5D%20Neural%20Factorization%20Machines%20for%20Sparse%20Predictive%20Analytics.pdf)
- [[2017][ZJU][AFM] Attentional Factorization Machines - Learning the Weight of Feature Interactions via Attention Networks](Rank/%5B2017%5D%5BZJU%5D%5BAFM%5D%20Attentional%20Factorization%20Machines%20-%20Learning%20the%20Weight%20of%20Feature%20Interactions%20via%20Attention%20Networks.pdf)
- [[2017][NUS][NCF] Neural Collaborative Filtering](Rank/%5B2017%5D%5BNUS%5D%5BNCF%5D%20Neural%20Collaborative%20Filtering.pdf)
- [[2017][Alibaba][MLR] Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction](Rank/%5B2017%5D%5BAlibaba%5D%5BMLR%5D%20Learning%20Piece-wise%20Linear%20Models%20from%20Large%20Scale%20Data%20for%20Ad%20Click%20Prediction.pdf)
- [[2017][Huawei][DeepFM] A Factorization-Machine based Neural NeExcerpt of 190,528 characters
Read on GitHub
207
3
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:fa48440ed0794125, topic:contrastive-learning
matched fp:fa48440ed0794125, topic:reinforcement-learning
matched fp:fa48440ed0794125, topic:papers