2021 Spring Special Lectures on Databases (Recsys)

조교: 김준엽, 김성재

강의안내

• 강의 시간: 월, 수 15:30 - 16:45
• 강의실: http://etl.snu.ac.kr/course/view.php?id=192814
• 이메일: lecture@europa.snu.ac.kr, 메일 제목 처음에 '[데이터베이스특강]'를 붙여주세요.

공지사항

• 수업 관련 안내
  • 코로나19 사태로 강의는 ETL에 올라오는 MS Zoom을 이용한 비대면 수업으로 진행됩니다. 학생용매뉴얼
  • ETL의 온라인 강의 링크(Zoom)를 확인하고 수업에 늦지 않게 입장해주세요!
• 메일 발송 규칙 안내
  • 조교 메일로 발송하는 모든 메일에는 제목 처음에 '[데이터베이스특강]'를 붙여야 조교들이 수신 가능합니다.
• PDF 비밀번호: 강의 시간에 안내(잊어버린 경우 이름과 학번을 포함하여 이메일로 보내시기 바랍니다)
• 발표자료는 꼭 발표 하루 전 23:59까지 메일로 보내주세요!!
• 발표는 한국어로 하시면 됩니다.

Term Projects

• Project 1 - Content-based Recommendation
  • Due date: 3/31(수) 23:59까지
  • Assignment (v1)
  • Base code (다운로드)

• Project 2 - Neighborhood-based / Model-Based Recommendation
  • Due date: 4/28(수) 23:59까지
  • Assignment (v1, v2)
  • Data (다운로드)

• Project 3 - Deep learning based Recommendation
  • Due date: 5/30(일) 23:59까지
  • Assignment (v1)
  • Data (다운로드)

Lecture Notes & Presentation Slides

• Week1
  •  [3/3] Introduction (수업자료)
• Week2
  •  [3/8] (continued)
  •  [3/10] Content-Based & Knowledge-Based Recommendation (수업자료)
• Week3
  •  [3/15] Neighborhood-Based Collaborative Filtering (수업자료)
  •  [3/17] Data Mining Review for RecSys (수업자료)
• Week4
  •  [3/22] Discussion
    • R. J. Mooney & L. Roy. Content-based book recommending using learning for text categorization. ACM Digital Libraries, 2000. (paper_01) (나현수, 신윤열)
    • G. Adomavicius & A. Tuzhilin. Using Data Mining Methods to Build Customer Profiles, IEEE Computer, vol. 34 no. 2, 2001. (paper_02) (김지연, 김형준)
  •  [3/24] Discussion
    • M. De Gemmis, et al. Integrating tags in a semantic content-based recommender. RecSys, 2008. (paper_03) (김재용, 김연아)
    • B. Smyth. Case-Based Recommendation. The Adaptive Web. 2007. (paper_04) (박충현, 한민희)
• Week5
  •  [3/29] Discussion
    • A. Felfernig & R. Burke, Constraint-based recommender systems: technologies and research issues, ICEC, 2008. (paper_05) (권영천, 안규수)
    • R. Jin, et al. An automatic weighting scheme for collaborative filtering. SIGIR, 2004. (paper_06) (문상우, 박민주)
  •  [3/31] Model-Based Collaborative Filtering (수업자료)
• Week6
  •  [4/5] Discussion
    • J. Wang, et al. Unifying user-based and item-based similarity approaches by similarity fusion. SIGIR, 2006. (paper_07) (고병현, 최영은)
    • B. Sarwar, et al, Application of dimensionality reduction in recommender system - a case study, WebKDD, 2000. (paper_08) (김종진, 박민혜)
  •  [4/7] Discussion
    • Y. Koren. Factorization meets the neighborhood: a multifaceted collaborative filtering model. KDD, 2008. (paper_09) (손영준, 이원도)
    • P. Cremonesi, et al. Performance of recommender algorithms on top-n recommendation tasks. RecSys, 2010. (paper_10) (성기홍, 안규수)
• Week7
  •  [4/12] Discussion
    • X. Ning & G. Karypis. SLIM: Sparse linear methods for top-N recommender systems. ICDM. 2011. (paper_11) (문상우, 김종진)
    • M. Gori & A. Pucci. Itemrank: a random-walk based scoring algorithm for recommender engines. IJCAI. 2007. (paper_12) (이원도, 최영은)
  •  [4/14] Midterm
• Week8
  •  [4/19] Hybrid RS & Evaluations (수업자료)
  •  [4/21] Discussion
    • R. Gemulla, et al. Large-scale matrix factorization with distributed stochastic gradient descent. KDD. 2011. (paper_13) (박민주, 박민혜)
    • M. Pazzani, A framework for collaborative, content-based and demographic filtering. Artificial Intelligence Rev. 13(5-6), 1999. (paper_14) (고병현)
• Week9
  •  [4/26] Context-Awareness (수업자료)
  •  [4/28]  [5/1] Discussion
    • A. Karatzoglou, et al. Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering. RecSys, 2010. (paper_15) (최현지, 김정우)
    • S. Rendle. Factorization machines. ICDM, 2010. (paper_16) (윤희승, 권영천)
• Week10
  •  [5/3]  Discussion
    • Yifan Hu, et al. Collaborative Filtering for Implicit Feedback Datasets, ICDM, 2008 (paper_17) (손영준, 윤희승)
    • Y. Koren. Collaborative filtering with temporal dynamics. KDD. 2009. (paper_18) (안규수, 성기홍)
• Week11
  •  [5/10] Deep Learning & Other Topics (수업자료)
  •  [5/12] Discussion
    • J. Levandoski, et al. LARS: A location-aware recommender system. ICDE. 2012. (paper_19) (김재용, 정현우, 최영은)
    • X. He, et al. Neural collaborative filtering. WWW. 2017. (paper_20) (박민혜, 나현수, 한민희)
• Week12
  •  [5/17] Discussion
    • R. He & J. McAuley. VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback. AAAI. 2016. (paper_21) (김형준, 신윤열)
    • H. Guo, et al. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction. IJCAI. 2017. (paper_22) (최현지, 김연아)
• Week13
  •  [5/24] Discussion
    • B. Hidasi, et al. Session-based recommendations with recurrent neural networks. ICLR. 2016. (paper_23) (정현우, 박충현, 성기홍)
    • J. Wang, et al. IRGAN: A Minimax Game for Unifying Generative and Discriminative IR Models. SIGIR. 2017. (paper_24) (김재용, 고병현)
  •  [5/26] Commercial Recommender Systems (수업자료)
• Week14
  •  [5/31] Discussion
    • X Wang, et al. Neural Graph Collaborative Filtering, SIGIR, 2019 (paper_27) (신윤열, 윤희승, 김정우)
    • F Sun, et al. BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer, CIKM, 2019 (paper_28) (정현우, 권영천)
  •  [6/2] Discussion
    • H. Ma, et al. Learning to recommend with social trust ensemble. SIGIR, 2009. (paper_29) (한민희, 문상우)
    • J. Herlocker, et al, Explaining collaborative filtering recommendations, CSCW, 2000. (paper_30) (손영준, 김연아)
• Week15
  •  [6/7] Discussion
    • S. Wang, et al. Attention-Based Transactional Context Embedding for Next-Item Recommendation. AAAI. 2018. (paper_25) (박충현, 김종진)
    • WC Kang, et al. Self-Attentive Sequential Recommendation, ICDM, 2018 (paper_26) (최현지, 이원도)
  •  [6/9] Discussion
    • Q Liu, et al. DeepStyle: Learning User Preferences for Visual Recommendation, SIGIR, 2017 (paper_31) (나현수, 김형준)
    • P, Covington, et al. Deep neural networks for youtube recommendations. RecSys. 2016. (paper_32) (박민주, 김정우)
  •  [6/12] Q&A 14:30 - 17:00
• Week16
  •  [6/14] Final Exam