推荐系统,是指根据用户的习惯、偏好或兴趣,从不断到来的大规模信息中识别满足用户兴趣的信息的过程。推荐推荐任务中的信息往往称为物品(Item)。根据具体应用背景的不同,这些物品可以是新闻、电影、音乐、广告、商品等各种对象。推荐系统利用电子商务网站向客户提供商品信息和建议,帮助用户决定应该购买什么产品,模拟销售人员帮助客户完成购买过程。个性化推荐是根据用户的兴趣特点和购买行为,向用户推荐用户感兴趣的信息和商品。随着电子商务规模的不断扩大,商品个数和种类快速增长,顾客需要花费大量的时间才能找到自己想买的商品。这种浏览大量无关的信息和产品过程无疑会使淹没在信息过载问题中的消费者不断流失。为了解决这些问题,个性化推荐系统应运而生。个性化推荐系统是建立在海量数据挖掘基础上的一种高级商务智能平台,以帮助电子商务网站为其顾客购物提供完全个性化的决策支持和信息服务。

知识荟萃

入门学习

  1. 探索推荐引擎内部的秘密,第 1 部分 推荐引擎初探 IBM developerWorks

  2. 探索推荐引擎内部的秘密,第 2 部分 深入推荐引擎相关算法 - 协同过滤

  3. 探索推荐引擎内部的秘密,第 3 部分 深入推荐引擎相关算法 - 聚类

  4. 项亮《推荐系统实践》笔记(1,2)

  5. 推荐算法综述(一,二,三,四,五)

  6. 推荐系统,第一部分 方法和算法简介 第 2 部分 开源引擎简介

  7. 深度学习在推荐系统中的一些应用

  8. 《纽约时报》如何打造新一代推荐系统

  9. 深度学习在推荐算法上的应用进展

  10. 如何学习推荐系统? by 知乎

  11. 了解关于系统推荐算法的知识,有什么好的资源推荐? by 知乎

  12. 项亮_推荐系统_博士论文.pdf

  13. 微信公众号:resyschina 中国最专业的个性化推荐技术与产品社区。

  14. 饿了么推荐系统:从0到1

  15. 【直播回顾】21天搭建推荐系统:实现“千人千面”个性化推荐(含视频)

  16. 这本书收录了推荐系统很多经典论文,话题涵盖非常广,第三章专门讲内容推荐的基本原理,第九章是一个具体的基于内容推荐系统的案例。 - 2010

    https://book.douban.com/subject/3695850/

  17. Deep Learning Meets Recommendation Systems by Wann-Jiun. https://blog.nycdatascience.com/student-works/deep-learning-meets-recommendation-systems/

  18. Machine Learning for Recommender systems Source: https://medium.com/recombee-blog/machine-learning-for-recommender-systems-part-1-algorithms-evaluation-and-cold-start-6f696683d0ed

  19. Check out our new client-side integration support and deploy personalized recommendations faster

    https://medium.com/recombee-blog/check-out-our-new-client-side-integration-support-and-deploy-personalized-recommendations-faster-7dd7bf5b6241

  20. Practical Recommender Systems by Kim Falk (Manning Publications). Chapter 1

    https://www.manning.com/books/practical-recommender-systems

  21. Recommender Systems Handbook by Ricci, F. et al.

    https://dl.acm.org/citation.cfm?id=1941884

综述

  1. Deep Learning based Recommender System: A Survey and New Perspectives 用于推荐系统的所有深度学习方法

    [https://arxiv.org/pdf/1707.07435.pdf]

  2. Toward the next generation of recommender systems:A survey of the state-of-the-art and possiblie extensions (2005), Adomavicius G, Tuzhilin A. http://people.stern.nyu.edu/atuzhili/pdf/TKDE-Paper-as-Printed.pdf

  3. Recommender systems: an introduction (2011), Zanker M, Felfernig A, Friedrich G.

    http://recommenderbook.net/media/szeged.pdf

  4. 推荐系统调研报告及综述-张永锋

    http://yongfeng.me/attach/rs-survey-zhang.pdf

  5. 综述论文合集-hongleizhang 2002-2019

    https://github.com/hongleizhang/RSPapers/tree/master/01-Surveys

  6. 知识图谱的推荐系统综述

    http://html.rhhz.net/tis/html/201805001.htm

  7. Recommender-System论文、学习资料以及业界分享

    https://github.com/zhaozhiyong19890102/Recommender-System

  8. RecommenderSystem-paper/Survey - daicoolb

    https://github.com/daicoolb/RecommenderSystem-Paper/tree/master/Survey

进阶文章

1997

  1. Recommender system (1997), P Resnick, HR Varian.

1998

  1. Empirical analysis of predictive algorithms for collaborative filtering (1998), John S Breese, David Heckerman, Carl M Kadie.
    [http://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/tr-98-12.pdf]
  2. Clustering methods for collaborative filtering (1998), Ungar, L. H., D. P. Foster.
    [http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.44.7783&rep=rep1&type=pdf]

1999

  1. A bayesian model for collaborative filtering (1999),Chien Y H, George E I.
    [http://www-stat.wharton.upenn.edu/~edgeorge/Research_papers/Bcollab.pdf]
  2. Using probabilistic relational models for collaborative filtering (1999), Lise Getoor, Mehran Sahami [http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=52BCC5212B0117CBB8BA48A1D8230E30?doi=10.1.1.40.4507&rep=rep1&type=pdf]

2001

  1. Item-based Collaborative Filtering Recommendation Algorithms (2001), Badrul M Sarwar, George Karypis, Joseph A Konstan, John Riedl. [http://www10.org/cdrom/papers/pdf/p519.pdf]

2002

  1. Hybrid recommender systems: Survey and experiments (2002), Burke R. [https://www.researchgate.net/profile/Robin_Burke/publication/263377228_Hybrid_Recommender_Systems_Survey_and_Experiments/links/5464ddc20cf2f5eb17ff3149.pdf]

2003

  1. Amazon Recommendations Item-to-Item Collaborative Filtering (2003), G Linden, B Smith, et al.
    [http://www.cs.umd.edu/~samir/498/Amazon-Recommendations.pdf]

2004

  1. A maximum entropy approach for collaborative filtering (2004), Browning J, Miller D J.
    [http://www.yaroslavvb.com/papers/browning-maximum.pdf]
  2. Supporting user query relaxation in a recommender system (2004),Mirzadeh N, Ricci F, Bansal M. [https://www.researchgate.net/profile/Francesco_Ricci5/publication/221017551_Supporting_User_Query_Relaxation_in_a_Recommender_System/links/0deec524dcde30df0d000000.pdf]

2005

  1. Case-based recommender systems: a unifying view.Intelligent Techniques for Web Personalization (2005),Lorenzi F, Ricci F. [www.inf.unibz.it/~ricci//papers/LorenziRicciCameraReady.pdf]
  2. SVD-based collaborative filtering with privacy (2005), Polat H, Du W.
    [http://www.cis.syr.edu/~wedu/Research/paper/sac2004.pdf]

2007

  1. Improving regularized singular value decomposition for collaborative filtering (2007), A Paterek.
    [http://www.mimuw.edu.pl/~paterek/ap_kdd.pdf]
  2. Predicting Clicks Estimating the click-through rate for new ads (2007),M Richardson, E Dominowska.
    [http://research.microsoft.com/en-us/um/people/mattri/papers/www2007/predictingclicks.pdf]
  3. Restricted Boltzmann Machines for Collaborative Filtering (2007),R Salakhutdinov, A Mnih, G Hinton. [http://machinelearning.wustl.edu/mlpapers/paper_files/icml2007_SalakhutdinovMH07.pdf]

2008

  1. Bayesian Probabilistic Matrix Factorization using Markov Chain Monte Carlo (2008),R Salakhutdinov, et al.
    [http://www.cs.utoronto.ca/~amnih/papers/bpmf.pdf]
  2. Factorization Meets the Neighborhood- a Multifaceted Collaborative Filtering Model (2008),Y Koren. [http://www.academia.edu/download/35945687/Factorization_meets_the_neighborhood_a_multifaceted_collaborative_filtering_model.pdf]

2009

  1. Utility-based repair of inconsistent requirements (2009), Felfernig A, Mairitsch M, Mandl M, et al.
    [http://link.springer.com/content/pdf/10.1007/978-3-642-02568-6_17.pdf]
  2. Bayesian Personalized Ranking from Implicit Feedback (2009), S Rendle, C Freudenthaler, Z Gantner.
    [https://arxiv.org/ftp/arxiv/papers/1205/1205.2618.pdf]
  3. Fast computation of query relaxations for knowledge-based recommenders (2009),Jannach D.
    [http://ls13-www.cs.tu-dortmund.de/homepage/publications/jannach/Journal_AICOM09.pdf]
  4. A hybrid approach to item recommendation in folksonomies (2009), Wetzker R, Umbrath W, Said A.
    [http://www.dai-labor.de/fileadmin/Files/Publikationen/Buchdatei/wetzker_folksonomyrecommendation_esair2009_final.pdf]

2010

  1. Click-Through Rate Estimation for Rare Events in Online Advertising (2010),X Wang, W Li, Y Cui, R Zhang.
    [http://www.cs.cmu.edu/~./xuerui/papers/ctr.pdf]
  2. Web-Scale Bayesian Click-Through Rate Prediction for Sponsored Search Advertising in Microsoft's Bing Search Engine (2010), T Graepel, JQ Candela.
    [http://machinelearning.wustl.edu/mlpapers/paper_files/icml2010_GraepelCBH10.pdf]
  3. Rendle S, Schmidt-Thieme L. Pairwise interaction tensor factorization for personalized tag recommendation[C]//Proceedings of the third ACM international conference on Web search and data mining. ACM, 2010: 81-90.
    [https://www.ismll.uni-hildesheim.de/pub/pdfs/Rendle2010-PITF.pdf]
  4. Factor in the Neighbors- Scalable and Accurate Collaborative Filtering (2010), Y Koren.
    [http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.476.4158&rep=rep1&type=pdf]

2011

  1. Tag-aware recommender systems: a state-of-the-art survey (2011), Zhang Z K, Zhou T, Zhang Y C.
    [http://arxiv.org/pdf/1202.5820.pdf]
  2. Feature-Based Matrix Factorization (2011), T Chen, Z Zheng, Q Lu, W Zhang, Y Yu.
    [https://arxiv.org/pdf/1109.2271.pdf?ref=theredish.com/web)]

2012

  1. A Two-Stage Ensemble of Diverse Models for Advertisement Ranking in KDD Cup 2012 (2012),KW Wu, CS Ferng, CH Ho, AC Liang, CH Huang. [http://ntur.lib.ntu.edu.tw/retrieve/188498/03.pdf]
  2. Combining Factorization Model and Additive Forest for Collaborative Followee Recommendation (2012), T Chen, L Tang, Q Liu, D Yang, S Xie, X Cao, C Wu.
    [http://curtis.ml.cmu.edu/w/courses/images/4/4e/AdditiveForestChen.pdf]
  3. Rendle, Steffen. "Factorization machines with libfm." ACM Transactions on Intelligent Systems and Technology (TIST) 3.3 (2012): 57. [http://www.csie.ntu.edu.tw/~b97053/paper/Factorization%20Machines%20with%20libFM.pdf]
  4. Factorization Machines with libFM (2012),S Rendle.
    [http://www.csie.ntu.edu.tw/~b97053/paper/Factorization%20Machines%20with%20libFM.pdf]
  5. Rendle S. Factorization machines with libfm[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2012, 3(3): 57. [http://www.csie.ntu.edu.tw/~b97053/paper/Factorization%20Machines%20with%20libFM.pdf]
  6. Ensemble of Collaborative Filtering and Feature Engineered Models for Click Through Rate Prediction (2012), M Jahrer, A Toscher, JY Lee, J Deng.
    [https://pdfs.semanticscholar.org/eeb9/34178ea9320c77852eb89633e14277da41d8.pdf]

2013

  1. Van den Oord A, Dieleman S, Schrauwen B. Deep content-based music recommendation[C]//Advances in neural information processing systems. 2013: 2643-2651.
    [http://papers.nips.cc/paper/5004-deep-content-based-music-recommendation.pdf]
  2. Deep content-based music recommendation (2013), A Van den Oord, S Dieleman.
    [http://papers.nips.cc/paper/5004-deep-content-based-music-recommendation.pdf]
  3. A Hybrid Approach with Collaborative Filtering for Recommender Systems (2013), G Badaro, H Hajj, et al.
    [http://staff.aub.edu.lb/~we07/Publications/A%20Hybrid%20Approach%20with%20Collaborative%20Filtering%20for%20Recommender%20Systems.pdf]

2014

  1. Zhang T, Zhang T, Zhang T, et al. Gradient boosting factorization machines[C]// ACM Conference on Recommender Systems. ACM, 2014:265-272.
    [http://pdfs.semanticscholar.org/cd57/9e1e9cc350c3f7746e6ae6911a97e21ba27c.pdf]
  2. Practical Lessons from Predicting Clicks on Ads at Facebook(2014), X He, J Pan, O Jin, T Xu, B Liu, T Xu, Y Shi.
    [http://quinonero.net/Publications/predicting-clicks-facebook.pdf]

2015

  1. Simple and scalable response prediction for display advertising (2015),O Chapelle, E Manavoglu, R Rosales. [http://people.csail.mit.edu/romer/papers/TISTRespPredAds.pdf]
  2. AutoRec- Autoencoders Meet Collaborative Filtering (2015), Suvash Sedhain, Aditya Krishna Menon, et al.
    [http://users.cecs.anu.edu.au/~u5098633/papers/www15.pdf]
  3. Collaborative Deep Learning for Recommender Systems (2015), Hao Wang, N Wang, Dityan Yeung.
    [http://www.wanghao.in/mis/CDL.pdf]

2016

  1. Juan Y, Zhuang Y, Chin W S, et al. Field-aware factorization machines for CTR prediction[C]//Proceedings of the 10th ACM Conference on Recommender Systems. ACM, 2016: 43-50.
    [http://ntucsu.csie.ntu.edu.tw/~cjlin/papers/ffm.pdf]
  2. Zhang W, Du T, Wang J, et al. Deep Learning over Multi-field Categorical Data[C]. european conference on information retrieval, 2016: 45-57. [https://arxiv.org/abs/1601.02376]
  3. Factorization Meets the Item Embedding- Regularizing Matrix Factorization with Item Co-occurrence (2016), D Liang, J Altosaar, L Charlin, DM Blei.
    [https://pdfs.semanticscholar.org/f14f/c33e0a351dff4f4e02510276604a93d1b9fa.pdf]
  4. F2M Scalable Field-Aware Factorization Machines (2016),C Ma, Y Liao, Y Wang, Z Xiao. [https://pdfs.semanticscholar.org/bb29/9887ba700300757de7560dc34b48b127cdca.pdf]
  5. Blondel M, Fujino A, Ueda N, et al. Higher-order factorization machines[C]//Advances in Neural Information Processing Systems. 2016: 3351-3359. [http://papers.nips.cc/paper/6144-higher-order-factorization-machines.pdf]
  6. Shan Y, Hoens T R, Jiao J, et al. Deep Crossing: Web-scale modeling without manually crafted combinatorial features[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016: 255-262.
    [www.kdd.org/kdd2016/papers/files/adf0975-shanA.pdf]
  7. Chen J, Sun B, Li H, et al. Deep ctr prediction in display advertising[C]//Proceedings of the 2016 ACM on Multimedia Conference. ACM, 2016: 811-820.
    [https://arxiv.org/pdf/1609.06018.pdf]
  8. Hybrid Collaborative Filtering with Autoencoders (2016), F Strub, J Mary, R Gaudel.
    [https://arxiv.org/pdf/1603.00806)]
  9. Wide & Deep Learning for Recommender Systems (2016),HT Cheng, L Koc, J Harmsen, T Shaked.
    [https://arxiv.org/pdf/1606.07792)]
  10. Deep Neural Networks for YouTube Recommendations (2016), Paul Covington, Jay Adams, Emre Sargin. [https://www.researchgate.net/publication/307573656_Deep_Neural_Networks_for_YouTube_Recommendations)]

2017

  1. He X, Chua T S. Neural Factorization Machines for Sparse Predictive Analytics[J]. 2017:355-364.
    [https://arxiv.org/pdf/1708.05027.pdf]
  2. Ning Y, Shi Y, Hong L, et al. A Gradient-based Adaptive Learning Framework for E icient Personal Recommendation[J]. 2017. [http://people.cs.vt.edu/naren/papers/recs254-ningA.pdf]
  3. Qu Y, Cai H, Ren K, et al. Product-Based Neural Networks for User Response Prediction[C]// IEEE, International Conference on Data Mining. IEEE, 2017:1149-1154.
    [https://arxiv.org/pdf/1611.00144.pdf]
  4. Guo H, Tang R, Ye Y, et al. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction[C]// Twenty-Sixth International Joint Conference on Artificial Intelligence. 2017:1725-1731.
    [https://arxiv.org/pdf/1703.04247.pdf]
  5. Xiao J, Ye H, He X, et al. Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks[J]. 2017. [https://ru.arxiv.org/pdf/1708.04617.pdf]
  6. A Hybrid Collaborative Filtering Model with Deep Structure for Recommender Systems (2017),Xin Dong, Lei Yu, Zhonghuo Wu, Yuxia Sun, Lingfeng Yuan, Fangxi Zhang.
    [http://www.aaai.org/ocs/index.php/AAAI/AAAI17/paper/download/14676/13916)]
  7. Collaborative Deep Embedding via Dual Networks (2017), Yilei Xiong, Dahua Lin, et al.
    [https://openreview.net/pdf?id=r1w7Jdqxl)]
  8. Recurrent Recommender Networks (2017), Chao-Yuan Wu.
    [http://delivery.acm.org/10.1145/3020000/3018689/p495-wu.pdf?ip=221.226.125.130&id=3018689&acc=OA&key=4D4702B0C3E38B35%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35%2E5945DC2EABF3343C&CFID=995126498&CFTOKEN=96329132&acm=1508034746_8da751768f4ee19af912968914bbbaa6)_]

2018

2019

Tutorial

  1. Tutorial: Recommender Systems IJCAI 2013

    [http://ijcai13.org/files/tutorial_slides/td3.pdf]

  2. Tutorial: Context In Recommender Systems 2016

    [https://www.slideshare.net/irecsys/tutorial-context-in-recommender-systems]

  3. 融合用户上下文的个性化推荐 张敏, 清华大学

    [http://www.cips-smp.org/smp2017/public/workshop-recommendation.html]

  4. 今日头条的人工智能技术实践 曹欢欢博士

    [http://www.cips-smp.org/smp2017/public/workshop-recommendation.html]

  5. 基于循环神经网络的序列推荐 吴书

    [http://www.cips-smp.org/smp2017/public/workshop-recommendation.html]

  6. 冷启动推荐的思考与进展 赵鑫

    [http://www.cips-smp.org/smp2017/public/workshop-recommendation.html]

  7. Recommender Systems: A Brief Introduction 中科大 刘淇 [http://home.ustc.edu.cn/~zengxy/dm/courseware/A%20brief%20introduction%20to%20RecSys.pdf]

  8. Deep Learning for Recommender Systems by Balázs Hidasi. RecSys Summer School, 21-25 August, 2017, Bozen-Bolzano.

https://www.slideshare.net/balazshidasi/deep-learning-in-recommender-systems-recsys-summer-school-2017

  1. Deep Learning for Recommender Systems by Alexandros Karatzoglou and Balázs Hidasi. RecSys2017 Tutorial.

    https://www.slideshare.net/kerveros99/deep-learning-for-recommender-systems-recsys2017-tutorial

  2. Introduction to recommender Systems by Miguel González-Fierro.

    https://github.com/miguelgfierro/sciblog_support/blob/master/Intro_to_Recommendation_Systems/Intro_Recommender.ipynb

  3. Collaborative Filtering using a RBM by Big Data University.

    https://github.com/santipuch590/deeplearning-tf/blob/master/dl_tf_BDU/4.RBM/ML0120EN-4.2-Review-CollaborativeFilteringwithRBM.ipynb

  4. Building a Recommendation System in TensorFlow: Overview.

    https://cloud.google.com/solutions/machine-learning/recommendation-system-tensorflow-overview

视频教程

  1. 如何设计一个推荐系统

    [https://www.youtube.com/watch?v=MZkxusQ6GNo]

  2. Recommender Systems | Coursera [https://www.coursera.org/specializations/recomender-systems]

  3. 大数据推荐系统算法视频教程

    https://pan.baidu.com/s/1U89CR_ZH_1JzsPOOKLbMyQ%E8%AF%B7%E6%B7%BB%E5%8A%A0%E9%93%BE%E6%8E%A5%E6%8F%8F%E8%BF%B0

    提取码:5ipq

  4. Introduction to Recommender Systems

    https://www.classcentral.com/course/recsys-1029

代码

  1. annoy - Approximate Nearest Neighbors in Python optimized for memory usage. [https://github.com/spotify/annoy]

  2. fastFM - A library for Factorization Machines. [https://github.com/ibayer/fastFM]

  3. implicit - A fast Python implementation of collaborative filtering for implicit datasets. [https://github.com/benfred/implicit]

  4. libffm- A library for Field-aware Factorization Machine (FFM). [https://github.com/guestwalk/libffm]

  5. LightFM - A Python implementation of a number of popular recommendation algorithms.

    [https://github.com/lyst/lightfm]

  6. surprise - A scikit for building and analyzing recommender systems. [http://surpriselib.com]

  7. Crab- a python recommender based on the popular packages NumPy, SciPy, matplotlib. The main repository seems to be abandoned.

    [http://muricoca.github.io/crab/]

  8. RecQ

    https://github.com/hongleizhang/RecQ

  9. Recommender System Suits: An open source toolkit for recommender system

    https://github.com/hongleizhang/RSAlgorithms

  10. Surprise- is a Python scikit building and analyzing recommender systems.

    https://github.com/NicolasHug/Surprise

  11. SpotLight- Spotlight uses PyTorch to build both deep and shallow recommender models.

    https://github.com/maciejkula/spotlight

  12. Python-Recsys: A python library for implementing a recommender system.

    https://github.com/ocelma/python-recsys

  13. LibRec- A java library for the state-of-the-art algorithms in recommeder sytem.

    https://www.librec.net/

  14. SparkMovieLens- A scalable on-line movie recommender using Spark and Flask.

    https://github.com/jadianes/spark-movie-lens

  15. Elasticsearch- Building a Recommender with Apache Spark & Elasticsearch

    https://github.com/IBM/elasticsearch-spark-recommender

相关会议

  • KDD the community for data mining, data science and analytics.
  • AAAI promotes research in, and responsible use of, artificial intelligence.
  • WWW provides the world a premier forum for discussion and debate about the evolution of the Web, the standardization of its associated technologies, and the impact of those technologies on society and culture.
  • MM is the premier international conference in the area of multimedia within the field of computer science. Multimedia research focuses on integration of the multiple perspectives offered by different digital modalities including images, text, video, music, sensor data, spoken audio.
  • NIPS has a responsibility to provide an inclusive and welcoming environment for everyone in the fields of AI and machine learning.
  • ICML is the leading international machine learning conference and is supported by the International Machine Learning Society (IMLS).
  • CIKM provides an international forum for presentation and discussion of research on information and knowledge management, as well as recent advances on data and knowledge bases.
  • SIGIR is the Association for Computing Machinery’s Special Interest Group on Information Retrieval. Since 1963, we have promoted research, development and education in the area of search and other information access technologies.
  • Recsys is the most famous conference in recommender system.
  • WSDM (pronounced "wisdom") is one of the the premier conferences on web inspired research involving search and data mining.
  • ICDM draws researchers and application developers from a wide range of data mining related areas such as statistics, machine learning, pattern recognition, databases and data warehousing, data visualization, knowledge-based systems, and high performance computing.

领域专家

  1. 陈恩红

    从中国科技术大学教授,多媒体计算与通信教育部-微软重点实验室副主任。机器学习与数据挖掘、网络信息处理领的专家,相关研究获得国家杰出青年科学基金、教育部新世纪优秀人才计划等资助。曾担任KD、AAAI2012、ICDM、PAKDD、SDM3等30余个国际学术会议的程序委员。CCF理事、人工智能与模式识别专委会委员、数据库专委会委员、大数据专家委员会委员,中国人工智能学会理事,知识工程与分布智能专业委员会副主任委员、IEEE高级会员。 [http://staff.ustc.edu.cn/~cheneh/]

  2. 唐杰

    清华大学计算机系副教授、博士生导师。主要研究兴趣包括:社会网络分析、数据挖掘、机器学习和语义Web。研发了研究者社会网络ArnetMiner系统,吸引全球220个国家和地区432万独立IP的访问。荣获首届国家自然科学基金优秀青年基金,2012中国计算机学会青年科学家奖、2010年清华大学学术新人奖(清华大学40岁以下教师学术最高奖)、2011年北京市科技新星、IBM全球创新教师奖以及KDD’12 Best Poster Award、PKDD’11 Best Student Paper Runnerup和JCDL’12 Best Student Paper Nomination。 [http://keg.cs.tsinghua.edu.cn/jietang/]

  3. 张敏

    清华大学计算机科学与技术系副教授,博士生导师。主要研究领域为信息检索、个性化推荐、用户画像与建模、用户行为分析。现任智能技术与系统国家重点实验中心实验室科研副主任、网络与媒体技术教育部-微软重点实验室副主任。在重要的国际期刊和会议上发表多篇学术论文,包括JIR、IJCAI、SIGIR、WWW、CIKM、WSDM等,Google Scholar引用约2500次。已授权专利11项。担任重要国际期刊TOIS编委,国际会议WSDM 2017和AIRS2016程序委员会主席,SIGIR 2018 short paper主席, WWW,SIGIR,CIKM,WSDM等重要国际会议的领域主席或资深审稿人。现任中国中文信息学会理事,中国计算机学会高级会员。http://www.thuir.org/group/~mzhang/~

  4. 谢幸

    微软亚洲研究院首席研究院,中国科学技术大学简直博士生导师。研究方向为数据挖掘、社会计算、普适计算。谢幸博士于2001年7月加入微软亚洲研究院,现任首席研究员,中国科技大学兼职博士生导师,以及微软-中科大联合实验室主任。他1996年毕业于中国科技大学少年班,并于2001年在中国科技大学获得博士学位,师从陈国良院士。目前,他的团队在数据挖掘、社会计算和普适计算等领域展开创新性的研究。他在国际会议和学术期刊上发表了250余篇学术论文,共被引用20000余次,H指数63,1999年获首届微软学者奖,多次在KDD、ICDM等顶级会议上获最佳论文奖,并被邀请在HHME 2018, ASONAM 2017、Mobiquitous 2016、SocInfo 2015、W2GIS 2011等会议做大会主题报告。他是ACM、IEEE高级会员和计算机学会杰出会员,多次担任顶级国际会议程序委员会委员和领域主席等职位。他是ACM Transactions on Social Computing, ACM Transactions on Intelligent Systems and Technology、Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT)、Springer GeoInformatica、Elsevier Pervasive and Mobile Computing、CCF Transactions on Pervasive Computing and Interaction等杂志编委。他参与创立了ACM SIGSPATIAL中国分会,并曾担任ACM UbiComp 2011、PCC 2012、IEEE UIC 2015、以及SMP 2017等大会程序委员会共同主席。

    个人主页:http://dsxt.ustc.edu.cn/zj_js.asp?zzid=1074

    https://www.microsoft.com/en-us/research/people/xingx/

  5. 张永锋

    Rutgers大学计算机系助理教授。最近的研究集中在机器学习和数据挖掘、推荐和搜索系统、知识图和计算经济学的交叉上,包括1)解释机器学习及其在决策支持系统中的应用--开发可解释的机器学习理论和用于决策支持系统的算法,例如个性化推荐和搜索;2)基于神经网络建模和自然语言处理的对话搜索、推荐和QA算法;3)网络经济学---应用和分析基于Web的应用中的经济理论,如推荐、搜索和共享经济。我的团队也对"个性化X"感兴趣,包括个性化推荐、搜索、教育、聊天机器人等。

    个人主页:http://yongfeng.me/

  6. 何向南

    中国科学技术大学信息与技术学院、大数据学院教授。研究方向是信息检索、数据挖掘和多媒体分析。共发表会议期刊论文六十余篇,如SIGIR、WWW、KDD和MM,以及包括TKDE、TOIS和TMM在内的期刊。其推荐系统方面的工作获得了WWW 2018和ACM SIGIR 2016年度最佳论文奖的荣誉提名。此外还担任过几个顶级会议的高级PC成员,包括SIGIR、WWW、KDD和MM等,以及TKDE、TOIS和TMM等期刊的审稿人。

    个人主页:http://staff.ustc.edu.cn/~hexn/

  7. 刘淇

    中国科学技术大学副教授、博导。研究方向为数据挖掘、机器学习、推荐系统、社交网络分析.

    个人主页:http://staff.ustc.edu.cn/~qiliuql/

  8. 李晨亮

    武汉大学副教授。武大珞珈青年学者,大数据分析与人工智能研究所(副所长)。研究方向为信息检索、自然语言处理、统计学习、数据挖掘、社交媒体分析和挖掘。

    个人主页:http://www.lichenliang.net/zh.html

  9. 赵鑫

北京大学博士,中国人民大学信息学院教师。研究领域为社交数据挖掘和自然语言处理领域,共发表CCF A/B、SCI论文40余篇, Google Scholar引用1500余次。博士期间的研究工作主要集中在社交媒体用户话题兴趣建模研究,同时获得谷歌中国博士奖研金和微软学者称号。其中ECIR’11提出的Twitter-LDA成为短文本主题建模重要基准比较方法之一,单文引用次数近700次。目前主要关注与社会经济紧密相关的商业大数据挖掘,研究用户意图检测、用户画像以及推荐系统,将理论技术运用到实践之中,承担国家自然科学青年基金、北京市自然科学青年基金,入选第二届CCF“青年人才托举计划”。担任多个国际顶级期刊和学术会议评审、AIRS 2016出版主席、SMP 2017领域主席以及NLPCC 2017领域主席。 [http://playbigdata.com/batmanfly/]

  1. 刘奕群

    清华大学计算机科学与技术系副教授。主要研究兴趣集中在网络搜索引擎技术,尤其是基于用户行为分析方法改进搜索引擎性能这一研究领域。面对海量繁杂的网络数据与千差万别的用户行为,传统的信息检索、机器学习、自然语言处理技术在搜索引擎系统中的应用面临着极大的挑战。为应对这一挑战,利用搜索引擎海量规模的用户行为数据信息,发挥“用户群体智慧”的作用是非常必要的。基于这一思路,其在国家自然科学基金重点项目、青年项目、教育部博士点基金项目与清华—搜狐搜索技术联合实验室的支持下开展了一系列相关研究。

    个人主页:http://www.thuir.cn/group/~YQLiu/

  2. 唐建

    MILA-QuebecAI研究所和HEC蒙特利尔的助理教授。在此之前是密歇根大学和卡内基梅隆大学的博士后。2014-2016年间在微软亚研工作。

    个人主页:https://jian-tang.com/

  3. 谷文栋

    微信公众号 resyschina , ResysChina发起人

  4. 洪亮劼

    Etsy数据科学主管,前雅虎研究院高级研发经理

  5. Yehuda Koren

    Netflix Prize冠军队成员,曾就职雅虎,现就职于谷歌,代表文献:Matrix Factorization Techniques for Recommender Systems

  6. Jure Leskovec

    斯坦福大学计算机科学系副教授。研究重点是挖掘和建模大型的社会和信息网络,它们的进化,以及信息的扩散和对它们的影响。调查的问题是由大规模数据、网络和在线媒体推动的。

    个人主页:https://cs.stanford.edu/~jure/

  7. Hao Ma

    个人主页:https://www.haoma.io/

  8. Julian MaAuley

    加利福尼亚大学圣迭戈分校助理教授。研究方向为社交网络、数据挖掘、推荐系统。

    个人主页:https://cseweb.ucsd.edu/~jmcauley/

  9. Robin Burke

    科罗拉多大学波德分校教授。主要研究方向为个性化推荐系统。

    个人主页: https://www.colorado.edu/cmci/people/college-leadership/robin-burke

  10. Bamshad Mobasher

    Bamshad Mobasher博士,芝加哥的计算和数字媒体学院网络智能中心主任,计算机科学系教授和网络智能中心主任。他也是德保罗大学数据挖掘和预测分析中心的共同创始人和总监。

    个人主页:https://www.cdm.depaul.edu/Faculty-and-Staff/Pages/faculty-info.aspx?fid=653


初步版本,水平有限,有错误或者不完善的地方,欢迎大家提建议和补充,会一直保持更新,本文为专知内容组原创内容,未经允许不得转载,如需转载请发送邮件至fangquanyi@gmail.com 或 联系微信专知小助手(Rancho_Fang)

敬请关注http://www.zhuanzhi.ai 和关注专知公众号,获取第一手AI相关知识

最近更新:2019-12-9

VIP内容

数据稀疏和冷启动是当前推荐系统面临的两大挑战. 以知识图谱为表现形式的附加信息能够在某种程度上缓解数据稀疏和冷启动带来的负面影响, 进而提高推荐的准确度. 本文综述了最近提出的应用知识图谱的推荐方法和系统, 并依据知识图谱来源与构建方法、推荐系统利用知识图谱的方式, 提出了应用知识图谱的推荐方法和系统的分类框架, 进一步分析了本领域的研究难点. 本文还给出了文献中常用的数据集. 最后讨论了未来有价值的研究方向.

http://www.aas.net.cn/cn/article/doi/10.16383/j.aas.c200128

推荐系统推荐系统是一种向目标用户建议可能感兴趣物品的软件工具. 随着网络与现实信息的爆炸式增长, 越来越多的在线服务商为用户提供商品、音乐、电影等(以下统称为物品)的推荐服务. 推荐系统能够满足用户的个性化需求, 为在线服务商带来巨大商业价值. 同时, 推荐方法与系统的研究促进了偏好挖掘、大数据处理、决策支持等领域的相关理论和实践的飞速发展, 其学术价值也引起了广泛的关注.

推荐系统面临的重要挑战主要是数据稀疏性问题和冷启动问题. 数据稀疏问题指的是相对于数量庞大的用户和物品, 仅有少量的物品获得了用户的评价或者购买, 难以据此获得相似的用户或相似的物品, 使得传统推荐方法失效了. 冷启动问题指的是系统由于并不知道新加入用户的历史行为, 无法给他们推荐物品, 同样新加入的物品也由于没有被用户评价或购买过而无法被针对性的推荐.

推荐系统中通常利用附加信息来解决上述问题, 以提高性能. 附加信息(一般也称上下文信息)分为显式信息和隐式信息[1]. 显式信息是通过诸如物理设备感知、用户问询、用户主动设定等方式获取的与用户、物品相关联的上下文信息. 隐式信息即利用已有数据或周围环境间接获取的一些上下文信息, 例如可根据用户与系统的交互日志获取时间上下文信息.

近年来, 利用以知识图谱为表示形式的附加信息的推荐方法受到了学者们的关注. 知识图谱最初用于提升搜索系统的性能[2], 刻画了海量实体之间的多种关系, 具有网状结构, 能够用于推荐系统中来增强用户、物品之间联系的认知与解释, 从而提高推荐准确度. 本文综述了2015年~2019年发表在DLRS、RecSys、KDD、CIKM、NIPS、TIST、UMAP、SIGIR等会议和期刊中的利用知识图谱的推荐方法的文献, 共23篇. 在利用知识图谱的推荐系统中, 通常首先将收集到的用户信息、物品信息、在利用知识图谱的推荐系统中, 通常首先将收集到的用户信息、物品信息、用户历史行为等数据或者一些相关的外部数据表示成知识图谱的形式. 然后, 设计推荐算法, 利用知识图谱生成推荐. 此类推荐系统通常包含知识图谱构建和利用知识图谱产生推荐两个环节. 本文根据这两个环节中构建知识图谱数据的不同来源, 以及推荐方法中利用知识图谱信息的不同形式提出了分类框架, 并据此对相关文献进行了分类综述, 详情请参看本文第三章. 与本文最为相关是文献[3]. 该文献综述了2009年~2017年16篇利用知识图谱的推荐方法的文献. 本文在综述的文章数量上超过了文献[3]. 此外, 本文提出文献分类框架能够更好地覆盖新提出的方法.

本文第一章介绍了利用知识图谱的推荐方法的相关背景知识; 第二章对利用知识图谱的推荐方法文献进行分类与综述; 第三章整理了目前常用的推荐系统数据集和知识图谱数据集; 第四章、第五章分别讨论了应用知识图谱的推荐系统的研究难点与发展前景; 最后, 在第六章中对全文进行了总结.

成为VIP会员查看完整内容
0
14

最新内容

We introduce 3D-FRONT (3D Furnished Rooms with layOuts and semaNTics), a new, large-scale, and comprehensive repository of synthetic indoor scenes highlighted by professionally designed layouts and a large number of rooms populated by high-quality textured 3D models with style compatibility. From layout semantics down to texture details of individual objects, our dataset is freely available to the academic community and beyond. Currently, 3D-FRONT contains 18,797 rooms diversely furnished by 3D objects, far surpassing all publicly available scene datasets. In addition, the 7,302 furniture objects all come with high-quality textures. While the floorplans and layout designs are directly sourced from professional creations, the interior designs in terms of furniture styles, color, and textures have been carefully curated based on a recommender system we develop to attain consistent styles as expert designs. Furthermore, we release Trescope, a light-weight rendering tool, to support benchmark rendering of 2D images and annotations from 3D-FRONT. We demonstrate two applications, interior scene synthesis and texture synthesis, that are especially tailored to the strengths of our new dataset. The project page is at: https://tianchi.aliyun.com/specials/promotion/alibaba-3d-scene-dataset.

0
0
下载
预览

最新论文

We introduce 3D-FRONT (3D Furnished Rooms with layOuts and semaNTics), a new, large-scale, and comprehensive repository of synthetic indoor scenes highlighted by professionally designed layouts and a large number of rooms populated by high-quality textured 3D models with style compatibility. From layout semantics down to texture details of individual objects, our dataset is freely available to the academic community and beyond. Currently, 3D-FRONT contains 18,797 rooms diversely furnished by 3D objects, far surpassing all publicly available scene datasets. In addition, the 7,302 furniture objects all come with high-quality textures. While the floorplans and layout designs are directly sourced from professional creations, the interior designs in terms of furniture styles, color, and textures have been carefully curated based on a recommender system we develop to attain consistent styles as expert designs. Furthermore, we release Trescope, a light-weight rendering tool, to support benchmark rendering of 2D images and annotations from 3D-FRONT. We demonstrate two applications, interior scene synthesis and texture synthesis, that are especially tailored to the strengths of our new dataset. The project page is at: https://tianchi.aliyun.com/specials/promotion/alibaba-3d-scene-dataset.

0
0
下载
预览
Top