wir bieten...
Dekobild im Seitenkopf ISMLL
Veranstaltungen im Wintersemester 2016 / Master-Seminar: Context- and Time-Aware Recommender Systems

Recommender Systems are nowadays part of our everyday life. Every time we access to our online shop account, specific products are shown to us. Sometimes these suggestions are helpful, sometimes totally useless. But how are these suggestions generated? Is our behavior influencing the recommendation or do we get random suggestions?

We start investigating how Recommender Systems come with a list of relevant objects to be recommended to users. In order to do so, all students must gain basic knowledge of machine learning and be able to explain not only the algorithm used in the chosen paper, but also more basic ones like vanilla Matrix Factorization. We will then consider relevant issues and algorithms’ extensions such as Time Aware and Context Aware Recommender System for the solution of typical issues such as the cold start problem. At the end of the course the students should also be able to reconstruct the complete data history: form the data collection to the algorithm decision.

Please consider that the presentations' slides below are not error free and therefore cannot substitute the participation to the lectures and discussion in class.


25.10 Paper Reading How To

01.11 Paper Writing How To

08.11 Vanilla Matrix Factorization

  • Koren, Yehuda, Robert Bell, and Chris Volinsky. "Matrix factorization techniques for recommender systems." Computer 42.8 (2009): 30-37.
  • Hoyer, Patrik O. "Non-negative matrix factorization with sparseness constraints." Journal of machine learning research 5.Nov (2004): 1457-1469.
  • Salakhutdinov, Ruslan, and Andriy Mnih. "Probabilistic matrix factorization." NIPS. Vol. 20. 2011.
    Group 1 Slides [PDF]15.11.16

15.11 The Cold Start Problem

  • Pilászy, I. and Tikk, D. (2009). Recommending new movies: Even a few ratings are more valuable than metadata. In RecSys
  • Park, Seung-Taek, and Wei Chu. "Pairwise preference regression for cold-start recommendation." Proceedings of the third ACM conference on Recommender systems. ACM, 2009.
  • Li, B., Zhu, X., Li, R., Zhang, C., Xue, X., and Wu, X. (2011). Cross-domain collaborative Filtering over time. In Proceedings of the Twenty-Second international joint conference on Artificial Intelligence
    Group 2 Slides [PDF]15.11.16

22.11 Online Update

  • Sarwar, Badrul, et al. "Incremental singular value decomposition algorithms for highly scalable recommender systems." Fifth International Conference on Computer and Information Science. 2002.
  • Vinagre, João, Alípio Mário Jorge, and João Gama. "Fast incremental matrix factorization for recommendation with positive-only feedback. "International Conference on User Modeling, Adaptation, and Personalization. Springer International Publishing, 2014.
  • Matuszyk, Pawel, et al. "Forgetting methods for incremental matrix factorization in recommender systems." Proceedings of the 30th Annual ACM Symposium on Applied Computing. ACM, 2015.
    Group 3 Slides [PDF]22.11.16

29.11 Implicit Feedback

  • Hu, Yifan, Yehuda Koren, and Chris Volinsky. "Collaborative filtering for implicit feedback datasets." 2008 Eighth IEEE International Conference on Data Mining. Ieee, 2008.
  • Pilászy, István, Dávid Zibriczky, and Domonkos Tikk. "Fast als-based matrix factorization for explicit and implicit feedback datasets."Proceedings of the fourth ACM conference on Recommender systems. ACM, 2010.
    Group 4 Slides [PDF]29.11.16

06.12 Ranking and Recommendation

  • Shi, Yue, et al. "CLiMF: learning to maximize reciprocal rank with collaborative less-is-more filtering." Proceedings of the sixth ACM conference on Recommender systems. ACM, 2012.
  • Lee, Guang-He, and Shou-De Lin. "LambdaMF: Learning Nonsmooth Ranking Functions in Matrix Factorization Using Lambda." Data Mining (ICDM), 2015 IEEE International Conference on. IEEE, 2015.
    Group 5 Slides [PDF]06.12.16

13.12 Collective Matrix Factorization

  • Bouchard, Guillaume, Dawei Yin, and Shengbo Guo. "Convex Collective Matrix Factorization." AISTATS. Vol. 13. 2013
  • Nickel, Maximilian, Volker Tresp, and Hans-Peter Kriegel. "A three-way model for collective learning on multi-relational data." Proceedings of the 28th international conference on machine learning (ICML-11). 2011
    Group 6 Slides [PDF]13.12.16

20.12 Time aware

  • Koren, Yehuda. "Collaborative filtering with temporal dynamics." Communications of the ACM53.4 (2010): 89-97.
  • Karatzoglou, Alexandros, et al. "Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering." Proceedings of the fourth ACM conference on Recommender systems. ACM, 2010.
    Group 7 Slides [PDF]22.12.16

10.01 Social Regularization

  • Ma, Hao, et al. "Sorec: social recommendation using probabilistic matrix factorization."Proceedings of the 17th ACM conference on Information and knowledge management. ACM, 2008.
  • Jamali, Mohsen, and Martin Ester. "A matrix factorization technique with trust propagation for recommendation in social networks." Proceedings of the fourth ACM conference on Recommender systems. ACM, 2010.
  • Ma, Hao, et al. "Recommender systems with social regularization." Proceedings of the fourth ACM international conference on Web search and data mining. ACM, 2011.
    Group 8 Slides [PDF]10.01.16

17.01 Recommendation in signed social networks

  • Tang, J., Aggarwal, C.,Liu, H. (2016, April). Recommendations in signed social networks. InProceedings of the 25th International Conference on World Wide Web (pp. 31-40). International World Wide Web Conferences Steering Committee.
  • Song, D., Meyer, D. A. (2015, January). Recommending Positive Links in Signed Social Networks by Optimizing a Generalized AUC. InAAAI (pp. 290-296).
  • Song, D., Meyer, D. A., Tao, D. (2015, August). Efficient latent link recommendation in signed networks. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1105-1114). ACM.
    Group 9 Slides [PDF]17.01.16

24.01 Graph knowledge

  • Menon, Aditya Krishna, and Charles Elkan. "Link prediction via matrix factorization." Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer Berlin Heidelberg, 2011.
  • Gu, Quanquan, Jie Zhou, and Chris HQ Ding. "Collaborative Filtering: Weighted Nonnegative Matrix Factorization Incorporating User and Item Graphs." SDM. 2010.
    Group 10 Slides [PDF]24.01.16

31.01 Tag Recommendation

  • Fang, Xiaomin, et al. "Personalized Tag Recommendation through Nonlinear Tensor Factorization Using Gaussian Kernel." AAAI. 2015.
  • Shin, Donghyuk, et al. "Tumblr blog recommendation with boosted inductive matrix completion." Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. ACM, 2015.
    Group 11 Slides [PDF]31.01.16


    Course Presentation[PDF]18.10.16
    Paper List[PDF]18.10.16
    How to read a scenitific paper[PDF]25.10.16
    How to write a summary paper and prepare your presentation[PDF]01.11.16
    Summary Paper Template [PDF]01.11.16
Betreuer: Carlotta Schatten
Zeit: Di 12-14 (s.t.)
Ort: A 9
Beginn: 18.10.2016
Zuordnung:MSc WI & IMIT
Modul- Handbuch:MHB
Voheriger Durchlauf:here