推荐系统,计算广告模型论文,代码与数据集汇总

这篇博客汇总了推荐系统、广告和搜索模型的最新研究,包括序列深度匹配模型、联合优化树型索引与深度模型、下一代查询广告匹配模型等。同时,涵盖了CTR/CVR排名模型,如Wide&Deep、DeepFM、xDeepFM等,并探讨了重排序、校准和竞价策略在实际系统中的应用。此外,还提供了多个开源资源链接,便于读者深入学习和实践。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

Rec-Models

更多细节参考项目:https://github.com/JackHCC/Rec-Models

https://github.com/JackHCC/Rec-Models
在这里插入图片描述

📝 Summary of recommendation, advertising and search models.

Recall

Papers

PaperResourceOthers
[2019阿里SDM模型] SDM: Sequential Deep Matching Model for Online Large-scale Recommender SystemCode
[2019阿里JTM] Joint Optimization of Tree-based Index and Deep Model for Recommender SystemsCode
[2019百度MOBIUS] MOBIUS:Towards the Next Generation of Qery Ad Matching in Baidu’s Sponsored SearchCode
[2019YouTube双塔] sampling bias corrected neural modeling for large corpus item recommendationsCode
[2018阿里TDM] Learning Tree-based Deep Model for Recommender SystemsCode
[2018Facebook] Collaborative Multi-modal deep learning for the personalized product retrieval in Facebook MarketplaceCode
[2013 DSSM模型] Learning deep structured semantic models for web search using clickthrough dataCode
[2008 SVD] Factorization Meets the Neighborhood: a Multifaceted Collaborative Filtering ModelCode
[2008] Collaborative Filtering for Implicit Feedback DatasetsCode

Ranking(CTR|CVR)

Papers

ModelPaperResourceOthers
Convolutional Click Prediction Model[CIKM 2015]A Convolutional Click Prediction ModelCCPM-基于卷积的点击预测模型Code
Factorization-supported Neural Network[ECIR 2016]Deep Learning over Multi-field Categorical Data: A Case Study on User Response PredictionCode
Product-based Neural Network[ICDM 2016]Product-based neural networks for user response predictionPNN论文笔记Code
Wide & Deep[DLRS 2016]Wide & Deep Learning for Recommender SystemsWide&Deep模型Code
DeepFM[IJCAI 2017]DeepFM: A Factorization-Machine based Neural Network for CTR Prediction深度推荐模型之DeepFMCode
Piece-wise Linear Model[arxiv 2017]Learning Piece-wise Linear Models from Large Scale Data for Ad Click PredictionMLR算法模型Code
Deep & Cross Network[ADKDD 2017]Deep & Cross Network for Ad Click Predictions谷歌经典 Deep&Cross Network原理Code
Attentional Factorization Machine[IJCAI 2017]Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks推荐算法精排模型AFM:Attentional Factorization MachinesCode
Neural Factorization Machine[SIGIR 2017]Neural Factorization Machines for Sparse Predictive AnalyticsNFM 模型 (论文精读)–广告&推荐Code
xDeepFM[KDD 2018]xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender SystemsxDeepFM 原理通俗解释及代码实战Code
Deep Interest Network[KDD 2018]Deep Interest Network for Click-Through Rate Prediction阿里巴巴DIN模型详解Code
Deep Interest Evolution Network[AAAI 2019]Deep Interest Evolution Network for Click-Through Rate PredictionDIEN算法学习笔记Code
AutoInt[CIKM 2019]AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural NetworksAutoInt:基于Multi-Head Self-Attention构造高阶特征Code
ONN[arxiv 2019]Operation-aware Neural Networks for User Response PredictionONN: paper+code readingCode
FiBiNET[RecSys 2019]FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate PredictionFiBiNET: paper reading + 实践调优经验Code
IFM[IJCAI 2019]An Input-aware Factorization Machine for Sparse PredictionIFM: 输入感知的FM模型Code
DCN V2[arxiv 2020]DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank SystemsDCNMix原理与实践Code
DIFM[IJCAI 2020]A Dual Input-aware Factorization Machine for CTR PredictionDIFM: 双重IFM模型Code
AFN[AAAI 2020]Adaptive Factorization Network: Learning Adaptive-Order Feature InteractionsCode
SharedBottom[arxiv 2017]An Overview of Multi-Task Learning in Deep Neural NetworksShared-Bottom网络结构Code
ESMM[SIGIR 2018]Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion RateESMM详解Code
MMOE[KDD 2018]Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts多任务学习之MMOE模型Code
PLE[RecSys 2020]Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations腾讯PCG RecSys2020最佳长论文——视频推荐场景下多任务PLE模型详解Code

Datasets

Reranking

Papers

PaperResourceOthers
[IJCAJ2018, Alibaba]. Globally Optimized Mutual Influence Aware Ranking in E-Commerce SearchCode
[SIGIR2018, Qingyao Ai]. Learning a Deep Listwise Context Model for Ranking RefinementCode
[RecSys2019, Alibaba]. Personalized Re-ranking for RecommendationCode
[CIKM2020, Alibaba]. EdgeRec-Recommender System on Edge in Mobile TaobaoCode
[Artix2021, Alibaba]. Revisit Recommender System in the Permutation ProspectiveCode

Blogs

Calibration

Papers

PaperResourceOthers
(KDD2020, Alibaba). Calibrating User Response Predictions in Online AdvertisingCode
(WWW2020, Tencent). A Simple and Empirically Strong Method for Reliable Probabilistic PredictionsCode
(WWW2022, Alibaba). MBCT Tree-Based Feature-Aware Binning for Individual Uncertainty CalibrationCode

Blogs

Bid

Papers

PaperResourceOthers
[IJCAI2017, Alibaba]. Optimized Cost per Click in Taobao Display AdvertisingCode
[KDD2019, Alibaba]. Bid Optimization by Multivariable Control in Display AdvertisingCode
[AAMAS2020, ByteDance]. Optimized Cost per Mille in Feeds AdvertisingCode
[KDD2021, Alibaba]. A Unified Solution to Constrained Bidding in Online Display AdvertisingCode
[KDD2014]. Optimal Real-Time Bidding for Display AdvertisingCode
[KDD2015]. Bid Landscape Forecasting in Online Ad Exchange MarketplaceCode
[KDD2015]. Predicting Winning Price in Real Time Bidding with Censored DataCode
[KDD2016]. User Response Learning for Directly Optimizing Campaign Performance in Display AdvertisingCode
[KDD2016]. Functional Bid Landscape Forecasting for Display AdvertisingCode
[KDD2017]. A Gamma-Based Regression for Winning Price Estimation in Real-Time Bidding AdvertisingCode
[KDD2018]. Bidding Machine Learning to Bid for Directly Optimizing Profits in Display AdvertisingCode
[KDD2019]. Deep Landscape Forecasting for Real-time Bidding AdvertisingCode

Blogs

Open Resource

评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

JackHCC

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值