推荐系统论文、学习资料、业界分享

动态更新工作中实现或者阅读过的推荐系统相关论文、学习资料和业界分享，作为自己工作的总结，也希望能为推荐系统相关行业的同学带来便利。 所有资料均来自于互联网，如有侵权，请联系王喆。同时欢迎对推荐系统感兴趣的同学与我讨论相关问题，我的联系方式如下：

• Email: wzhe06@gmail.com
• LinkedIn: 王喆的LinkedIn
• 知乎私信: 王喆的知乎

其他相关资源

• 计算广告相关论文和资源列表

• 张伟楠的RTB Papers列表

• 搜广推业界实践文章

• Honglei Zhang的推荐系统论文列表

目录

Retrieval and Rerank

• [Distillation] Distillation Based Multi-task Learning- A Candidate Generation Model for Improving Reading Duration

• [PRM] Personalized Re-ranking for Recommendation

• [COLD] Towards the Next Generation of Pre-ranking System

• [Seq2Slate] Re-ranking and Slate Optimization with RNNs

• [Hulu Diversity] Fast Greedy Map Inference for Determinantal Point Processes to Improve Recommendation Diversity

• [TDM] Learning Tree-based Deep Model for Recommender Systems

• [LTR] From RankNet to LambdaRank to LambdaMART- An Overview

• [AirBnb Rerank] Managing Diversity in Airbnb Search

• [Deep Retrieval] Learning a Retrievable Structure for Large-scale Recommendations

Deep Learning Recommender System

• [DCN] Deep & Cross Network for Ad Click Predictions (Stanford 2017)

• [Deep Crossing] Deep Crossing - Web-Scale Modeling without Manually Crafted Combinatorial Features (Microsoft 2016)

• [DIN] Deep Interest Network for Click-Through Rate Prediction (Alibaba 2018)

• [DL Recsys Intro] Deep Learning based Recommender System- A Survey and New Perspectives (UNSW 2018)

• [PinnerFormer] Sequence Modeling for User Representation at Pinterest

• [xDeepFM] xDeepFM - Combining Explicit and Implicit Feature Interactions for Recommender Systems (USTC 2018)

• [Image CTR] Image Matters - Visually modeling user behaviors using Advanced Model Server (Alibaba 2018)

• [CDL] Collaborative Deep Learning for Recommender Systems (HKUST, 2015)

• [DSSM in Recsys] A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems (Microsoft 2015)

• [AFM] Attentional Factorization Machines - Learning the Weight of Feature Interactions via Attention Networks (ZJU 2017)

• [DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction (Alibaba 2019)

• [Wide&Deep] Wide & Deep Learning for Recommender Systems (Google 2016)

• [DSSM] Learning Deep Structured Semantic Models for Web Search using Clickthrough Data (UIUC 2013)

• [NCF] Neural Collaborative Filtering (NUS 2017)

• [FNN] Deep Learning over Multi-field Categorical Data (UCL 2016)

• [DeepFM] A Factorization-Machine based Neural Network for CTR Prediction (HIT-Huawei 2017)

• [NFM] Neural Factorization Machines for Sparse Predictive Analytics (NUS 2017)

• [Latent Cross] Latent Cross- Making Use of Context in Recurrent Recommender Systems (Google 2018)

• [TransAct] Transformer-based Real-time User Action Model for Recommendation at Pinterest

Embedding

• [Negative Sampling] Word2vec Explained Negative-Sampling Word-Embedding Method (2014)

• [SDNE] Structural Deep Network Embedding (THU 2016)

• [Item2Vec] Item2Vec-Neural Item Embedding for Collaborative Filtering (Microsoft 2016)

• [Word2Vec] Distributed Representations of Words and Phrases and their Compositionality (Google 2013)

• [LSH] Locality-Sensitive Hashing for Finding Nearest Neighbors (IEEE 2008)

• [Word2Vec] Word2vec Parameter Learning Explained (UMich 2016)

• [GraphSAGE]Inductive Representation Learning on Large Graphs

• [Node2vec] Node2vec - Scalable Feature Learning for Networks (Stanford 2016)

• [Graph Embedding] DeepWalk- Online Learning of Social Representations (SBU 2014)

• [RippleNet] Propagating User Preferences on the Knowledge Graph for Recommender Systems

• [Airbnb Embedding] Real-time Personalization using Embeddings for Search Ranking at Airbnb (Airbnb 2018)

• [Alibaba Embedding] Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba (Alibaba 2018)

• [KGAT] Knowledge Graph Attention Network for Recommendation

• [Word2Vec] Efficient Estimation of Word Representations in Vector Space (Google 2013)

• [Explainable RS]Fairness-aware Explainable Recommendation over Knowledge Graphs

• [LINE] LINE - Large-scale Information Network Embedding (MSRA 2015)

Famous Machine Learning Papers

• [Attention] Attention is All You Need

• [RNN] Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation (UofM 2014)

• [CNN] ImageNet Classification with Deep Convolutional Neural Networks (UofT 2012)

Multi-Task

• [ESMM] Entire Space Multi-task Model- An Effective Approach for Estimating Post-click Conversion Rate

• [MMoE] Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts

• [PLE] Progressive Layered Extraction (PLE)- A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations

Feature Data and Infra

• [Privacy] Privacy-preserving News Recommendation Model Learning

• [EdgeRec] Recommender System on Edge in Mobile Taobao

• [MMKGs] Multi-modal Knowledge Graphs for Recommender Systems

• [Delayed Feedback] Capturing Delayed Feedback in Conversion Rate Prediction via Elapsed-time Sampling

• [Delayed Feedback] Handling Many Conversions Per Click in Modeling Delayed Feedback

• [ViLBERT] Pretraining Task-agnostic Visiolinguistic Representations for Vision-and-language Tasks

• [MM-Rec] Multimodal News Recommendation

Classic Recommender System

• [MF] Matrix Factorization Techniques for Recommender Systems (Yahoo 2009)

• [Earliest CF] Using Collaborative Filtering to Weave an Information Tapestry (PARC 1992)

• [Recsys Intro] Recommender Systems Handbook (FRicci 2011)

• [Recsys Intro slides] Recommender Systems An introduction (DJannach 2014)

• [CF] Amazon Recommendations Item-to-Item Collaborative Filtering (Amazon 2003)

• [ItemCF] Item-Based Collaborative Filtering Recommendation Algorithms (UMN 2001)

• [Bilinear] Personalized Recommendation on Dynamic Content Using Predictive Bilinear Models (Yahoo 2009)

LLM Recommender System

• [Once] Boosting Content-based Recommendation with Both Open-and Closed-source Large Language Models

• [PALR] Personalization Aware LLMs for Recommendation

• [Onesearch] A preliminary exploration of the unified end-to-end generative framework for e-commerce search

• [NoteLLM] A Retrievable Large Language Model for Note Recommendation

• [PMG] Personalized Multimodal Generation with Large Language Models

• [MTGR] Industrial-Scale Generative Recommendation Framework in Meituan

• [MoRecl] Where to Go Next for Recommender Systems? Id-vs. Modality-based Recommender Models

• [GR] Generative Recommendation- Towards Next-generation Recommender Paradigm

• [MetaGR] Actions Speak Louder than Words- Trillion-Parameter Sequential Transducers for Generative Recommendations

• [OneRec] Unifying Retrieve and Rank with Generative Recommender and Preference Alignment

• [ClickPrompt] CTR Models are Strong Prompt Generators for Adapting Language Models to CTR Prediction

• [Tiger] Recommender Systems with Generative Retrieval

Evaluation

• [EE Evaluation Intro] Offline Evaluation and Optimization for Interactive Systems (Microsoft 2015)

• [Bootstrapped Replay] Improving offline evaluation of contextual bandit algorithms via bootstrapping techniques (Ulille 2014)

• [InterLeaving] Large-Scale Validation and Analysis of Interleaved Search Evaluation (Yahoo 2012)

• [RecSim] A Configurable Simulation Platform for Recommender Systems

• [Replay] Unbiased Offline Evaluation of Contextual-bandit-based News Article Recommendation Algorithms (Yahoo 2012)

• [Eval Agent] User Behavior Simulation with Large Language Model based Agents

• [Classic Metrics] A Survey of Accuracy Evaluation Metrics of Recommendation Tasks (Microsoft 2009)

Reinforcement Learning in Reco

• [Active Learning] Active Learning in Collaborative Filtering Recommender Systems(UNIBZ 2014)

• [RL Music] Exploration in Interactive Personalized Music Recommendation- A Reinforcement Learning Approach (NUS 2013)

• [Active Learning] A survey of active learning in collaborative filtering recommender systems (POLIMI 2016)

• [DRN] A Deep Reinforcement Learning Framework for News Recommendation (MSRA 2018)

Industry Recommender System

• [Pinterest] Personalized content blending In the Pinterest home feed (Pinterest 2016)

• [Pinterest] Graph Convolutional Neural Networks for Web-Scale Recommender Systems (Pinterest 2018)

• [Airbnb] Search Ranking and Personalization at Airbnb Slides (Airbnb 2018)

• [Baidu slides] DNN in Baidu Ads (Baidu 2017)

• [Quora] Building a Machine Learning Platform at Quora (Quora 2016)

• [Airbnb] Optimizing Airbnb Search Journey with Multi-task Learning

• [Alibaba] Search-based User Interest Modeling with Lifelong Sequential Behavior Data for CTR Prediction

• [Alibaba Star] One Model to Serve All- Star Topology Adaptive Recommender for Multi-domain CTR Prediction

• [Netflix] The Netflix Recommender System- Algorithms, Business Value, and Innovation (Netflix 2015)

• [Youtube] Deep Neural Networks for YouTube Recommendations (Youtube 2016)

• [Alibaba] Capturing Conversion Rate Fluctuation During Sales Promotions- A Novel Historical Data Reuse Approach

• [Airbnb] Applying Deep Learning To Airbnb Search (Airbnb 2018)

• [Alibaba] Image Matters- Visually Modeling User Behaviors Using Advanced Model Server

Exploration and Exploitation

• [EE in Ads] Customer Acquisition via Display Advertising Using MultiArmed Bandit Experiments (UMich 2015)

• [EE in Ads] Exploitation and Exploration in a Performance based Contextual Advertising System (Yahoo 2010)

• [EE in AlphaGo]Mastering the game of Go with deep neural networks and tree search (Deepmind 2016)

• [UCB1] Bandit Algorithms Continued - UCB1 (Noel Welsh 2010)

• [Spotify] Explore, Exploit, and Explain- Personalizing Explainable Recommendations with Bandits (Spotify 2018)

• [TS Intro] Thompson Sampling Slides (Berkeley 2010)

• [Thompson Sampling] An Empirical Evaluation of Thompson Sampling (Yahoo 2011)

• [UCT] Exploration exploitation in Go UCT for Monte-Carlo Go (UPSUD 2016)

• [LinUCB] A Contextual-Bandit Approach to Personalized News Article Recommendation (Yahoo 2010)

• [RF in MAB]Random Forest for the Contextual Bandit Problem (Orange 2016)

• [EE Intro] Exploration and Exploitation Problem Introduction by Wang Zhe (Hulu 2017)

Cold Start and Debias

• [RS Bias] Bias and Debias in Recommender System- A Survey and Future Directions

• [Meta Emb]Warm Up Cold-start Advertisements- Improving CTR Predictions via Learning to Learn ID Embeddings

• [PAL] A Position-Bias Aware Learning Framework for CTR Prediction in Live Recommender Systems

• [DICE] Disentangling User Interest and Conformity for Recommendation with Causal Embedding