Article

Probabilistic matrix factorization with non-random missing data

Authors:

José Miguel Hernández-Lobato,

Zoubin GhahramaniAuthors Info & Claims

ICML'14: Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32

Pages II-1512 - II-1520

Published: 21 June 2014 Publication History

Abstract

We propose a probabilistic matrix factorization model for collaborative filtering that learns from data that is missing not at random (MNAR). Matrix factorization models exhibit state-of-the-art predictive performance in collaborative filtering. However, these models usually assume that the data is missing at random (MAR), and this is rarely the case. For example, the data is not MAR if users rate items they like more than ones they dislike. When the MAR assumption is incorrect, inferences are biased and predictive performance can suffer. Therefore, we model both the generative process for the data and the missing data mechanism. By learning these two models jointly we obtain improved performance over state-of-the-art methods when predicting the ratings and when modeling the data observation process. We present the first viable MF model for MNAR data. Our results are promising and we expect that further research on NMAR models will yield large gains in collaborative filtering.

References

[1]

Chu, Wei and Ghahramani, Zoubin. Gaussian processes for ordinal regression. In Journal of Machine Learning Research, pp. 1019-1041, 2005.

[2]

Ghahramani, Z. and Beal, M. J. Advanced Mean Field Method--Theory and Practice, chapter Graphical models and variational methods, pp. 161-177. 2001.

[3]

Gunawardana, Asela and Shani, Guy. A survey of accuracy evaluation metrics of recommendation tasks. The Journal of Machine Learning Research, 10:2935-2962, 2009.

[4]

Hoffman, Matthew D., Blei, David M., Wang, Chong, and Paisley, John. Stochastic variational inference. Journal of Machine Learning Research, 14:1303-1347, 2013.

[5]

Kschischang, Frank R., Frey, Brendan J., and Loeliger, H.-A. Factor graphs and the sum-product algorithm. IEEE Transactions on Information Theory, 47(2):498- 519, 2001.

[6]

Lakshminarayanan, Balaji, Bouchard, Guillaume, and Archambeau, Cedric. Robust Bayesian matrix factorisation. In International Conference on Artificial Intelligence and Statistics, pp. 425-433, 2011.

[7]

Little, R.J.A. and Rubin, D.B. Statistical Analysis With Missing Data. Wiley Series in Probability and Statistics - Applied Probability and Statistics Section Series. Wiley, 1987.

[8]

Marlin, Benjamin M. and Zemel, Richard S. Collaborative filtering and the missing at random assumption. In Proceedings of the 23rd Conference on Uncertainty in Artificial Intelligence, 2007.

[9]

Marlin, Benjamin M. and Zemel, Richard S. Collaborative prediction and ranking with non-random missing data. In Proceedings of the Third ACM Conference on Recommender Systems, RecSys '09, pp. 5-12, 2009.

[10]

Minka, Thomas P. Expectation propagation for approximate bayesian inference. In Proceedings of the Seventeenth conference on Uncertainty in Artificial Intelligence, pp. 362-369, 2001.

[11]

Mnih, Andriy and Salakhutdinov, Ruslan. Probabilistic matrix factorization. In Advances in neural information processing systems, pp. 1257-1264, 2007.

[12]

Paquet, Ulrich, Thomson, Blaise, andWinther, Ole. A hierarchical model for ordinal matrix factorization. Statistics and Computing, 22(4):945-957, 2012.

[13]

Rendle, Steffen, Freudenthaler, Christoph, Gantner, Zeno, and Schmidt-Thieme, Lars. BPR: Bayesian personalized ranking from implicit feedback. In Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, pp. 452-461, 2009.

[14]

Steck, Harald. Training and testing of recommender systems on data missing not at random. In Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '10, pp. 713-722, 2010.

[15]

Stern, David H, Herbrich, Ralf, and Graepel, Thore. Matchbox: large scale online bayesian recommendations. In Proceedings of the 18th international conference on World wide web, pp. 111-120. ACM, 2009.

Cited By

Zhang YBai YChang JZang XLu SLu JFeng FNiu YSong YFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling FrameworkProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3615483(4952-4959)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3615483
Jiang YJiao LZhao LZeng KJadliwala M(2022)Beam Pattern Fingerprinting with Missing Features for Spoofing Attack Detection in Millimeter-Wave NetworksProceedings of the 2022 ACM Workshop on Wireless Security and Machine Learning10.1145/3522783.3529522(75-80)Online publication date: 19-May-2022
https://dl.acm.org/doi/10.1145/3522783.3529522
Pan SLi DGu HLu TLuo XGu N(2022)Accurate and Explainable Recommendation via Review RationalizationProceedings of the ACM Web Conference 202210.1145/3485447.3512029(3092-3101)Online publication date: 25-Apr-2022
https://dl.acm.org/doi/10.1145/3485447.3512029
Show More Cited By

Index Terms

Probabilistic matrix factorization with non-random missing data
1. Computing methodologies
  1. Machine learning

Index terms have been assigned to the content through auto-classification.

Recommendations

Collaborative filtering using non-negative matrix factorisation

Collaborative filtering is a popular strategy in recommender systems area. This approach gathers users' ratings and then predicts what users will rate based on their similarity to other users. However, most of the collaborative filtering methods have ...
Kernelized probabilistic matrix factorization for collaborative filtering: exploiting projected user and item graph
RecSys '18: Proceedings of the 12th ACM Conference on Recommender Systems

Matrix Factorization (MF) techniques have already shown its strong foundation in collaborative filtering (CF), particularly for rating prediction problem. In the basic MF model, the use of additional information such as social network, item tags along ...
An Improved Neighborhood-Aware Unified Probabilistic Matrix Factorization Recommendation

Recommendation systems require sufficient information to provide proper recommendations. Both rating and tagging information can be used in social tagging systems. Many recommendation systems consider the relationships between users, items and tags, ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

ICML'14: Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32

June 2014

2786 pages

Publisher

JMLR.org

Publication History

Published: 21 June 2014

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

13
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 23 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Zhang YBai YChang JZang XLu SLu JFeng FNiu YSong YFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling FrameworkProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3615483(4952-4959)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3615483
Jiang YJiao LZhao LZeng KJadliwala M(2022)Beam Pattern Fingerprinting with Missing Features for Spoofing Attack Detection in Millimeter-Wave NetworksProceedings of the 2022 ACM Workshop on Wireless Security and Machine Learning10.1145/3522783.3529522(75-80)Online publication date: 19-May-2022
https://dl.acm.org/doi/10.1145/3522783.3529522
Pan SLi DGu HLu TLuo XGu N(2022)Accurate and Explainable Recommendation via Review RationalizationProceedings of the ACM Web Conference 202210.1145/3485447.3512029(3092-3101)Online publication date: 25-Apr-2022
https://dl.acm.org/doi/10.1145/3485447.3512029
Zhao LGao YYe JChen FYe YLu CRamakrishnan N(2021)Spatio-Temporal Event Forecasting Using Incremental Multi-Source Feature LearningACM Transactions on Knowledge Discovery from Data10.1145/346497616:2(1-28)Online publication date: 13-Sep-2021
https://dl.acm.org/doi/10.1145/3464976
Carraro DBridge DHung CCerny TShin DBechini A(2020)Debiased offline evaluation of recommender systemsProceedings of the 35th Annual ACM Symposium on Applied Computing10.1145/3341105.3375759(1435-1442)Online publication date: 30-Mar-2020
https://dl.acm.org/doi/10.1145/3341105.3375759
Shi SZhang MYu XZhang YHao BLiu YMa SZhu WTao DCheng XCui PRundensteiner ECarmel DHe QXu Yu J(2019)Adaptive Feature Sampling for Recommendation with Missing Content Feature ValuesProceedings of the 28th ACM International Conference on Information and Knowledge Management10.1145/3357384.3357942(1451-1460)Online publication date: 3-Nov-2019
https://dl.acm.org/doi/10.1145/3357384.3357942
Chae DKang JKim SChoi J(2019)Rating Augmentation with Generative Adversarial Networks towards Accurate Collaborative FilteringThe World Wide Web Conference10.1145/3308558.3313413(2616-2622)Online publication date: 13-May-2019
https://dl.acm.org/doi/10.1145/3308558.3313413
Liu HWen JJing LYu JBogers TSaid ABrusilovsky PTikk D(2019)Deep generative ranking for personalized recommendationProceedings of the 13th ACM Conference on Recommender Systems10.1145/3298689.3347012(34-42)Online publication date: 10-Sep-2019
https://dl.acm.org/doi/10.1145/3298689.3347012
Liu DLin CZhang ZXiao YTong HCulpepper JMoffat ABennett PLerman K(2019)Spiral of Silence in Recommender SystemsProceedings of the Twelfth ACM International Conference on Web Search and Data Mining10.1145/3289600.3291003(222-230)Online publication date: 30-Jan-2019
https://dl.acm.org/doi/10.1145/3289600.3291003
Qin XBlomstedt PLeppäaho EParviainen PKaski S(2019)Distributed Bayesian matrix factorization with limited communicationMachine Language10.1007/s10994-019-05778-2108:10(1805-1830)Online publication date: 1-Oct-2019
https://dl.acm.org/doi/10.1007/s10994-019-05778-2
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Table of Contents