Robust collaborative filtering

ABSTRACT

The widespread deployment of recommender systems has lead to user feedback of varying quality. While some users faithfully express their true opinion, many provide noisy ratings which can be detrimental to the quality of the generated recommendations. The presence of noise can violate modeling assumptions and may thus lead to instabilities in estimation and prediction. Even worse, malicious users can deliberately insert attack profiles in an attempt to bias the recommender system to their benefit.

Robust statistics is an area within statistics where estimation methods have been developed that deteriorate more gracefully in the presence of unmodeled noise and slight departures from modeling assumptions. In this work, we study how such robust statistical methods, in particular M-estimators, can be used to generate stable recommendation even in the presence of noise and spam. To that extent, we present a Robust Matrix Factorization algorithm and study its stability. We conclude that M-estimators do not add significant stability to recommendation; however the presented algorithm can outperform existing recommendation algorithms in its recommendation quality.

REFERENCES

• 1: Yossi Azar , Amos Fiat , Anna Karlin , Frank McSherry , Jared Saia, Spectral analysis of data, Proceedings of the thirty-third annual ACM symposium on Theory of computing, p.619-626, July 2001, Hersonissos, Greece [doi>10.1145/380752.380859]
• 2: R. Burke, B. Mobasher, C. Williams, and R. Bhaumik. Analysis and detection of segment-focused attacks against collaborative recommendation. 2006.
• 3: Paul-Alexandru Chirita , Wolfgang Nejdl , Cristian Zamfir, Preventing shilling attacks in online recommender systems, Proceedings of the 7th annual ACM international workshop on Web information and data management, November 04-04, 2005, Bremen, Germany [doi>10.1145/1097047.1097061]
• 4: A. Dempster, N. Laird, and D. Rubin. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, 39(1):1-38, 1977.
• 5: K. Gabriel and S. Zamir. Lower Rank Approximation of Matrices by Least Squares with Any Choice of Weights. Technometrics, 21(4):489-498, 1979.
• 6: G. Gorrell. Generalized hebbian algorithm for incremental singular value decomposition in natural language processing. In EACL, 2006.
• 7: Jon Herlocker , Joseph A. Konstan , John Riedl, An Empirical Analysis of Design Choices in Neighborhood-Based Collaborative Filtering Algorithms, Information Retrieval, v.5 n.4, p.287-310, October 2002 [doi>10.1023/A:1020443909834]
• 8: Thomas Hofmann, Latent semantic models for collaborative filtering, ACM Transactions on Information Systems (TOIS), v.22 n.1, p.89-115, January 2004 [doi>10.1145/963770.963774]
• 9: H. Hotelling. Analysis of a Complex of Statistical Variables Into Principal Components. 1933.
• 10: P. Huber. Robust Estimation of a Location Parameter. The Annals of Mathematical Statistics, 35(1):73--101, 1964.
• 11: P. Huber. Robust Statistics. Wiley-IEEE, 2004.
• 12: I. T. Jolliffe. Principal Component Analysis (2nd Edition). Springer, 2002.
• 13: Shyong K. Lam , John Riedl, Shilling recommender systems for fun and profit, Proceedings of the 13th international conference on World Wide Web, May 17-20, 2004, New York, NY, USA [doi>10.1145/988672.988726]
• 14: Xi Li , Zhengnan Ning , Liuwei Xiang, Robust 3D Reconstruction with Outliers Using RANSAC Based Singular Value Decomposition, IEICE - Transactions on Information and Systems, v.E88-D n.8, p.2001-2004, August 2005 [doi>10.1093/ietisy/e88-d.8.2001]
• 15: L. Liu, D. Hawkins, S. Ghosh, and S. Young. Robust singular value decomposition analysis of microarray data. Proceedings of the National Academy of Sciences, 100(23):13167--13172, 2003.
• 16: B. Mehta. Unsupervised shilling detection for collaborative filtering. In AAAI 2007: Proceedings of the 22nd Twenty-Second Conference on Artificial Intelligence, AAAI Press, Vancouver, Canada, 2007.
• 17: Bhaskar Mehta , Thomas Hofmann , Peter Fankhauser, Lies and propaganda: detecting spam users in collaborative filtering, Proceedings of the 12th international conference on Intelligent user interfaces, January 28-31, 2007, Honolulu, Hawaii, USA [doi>10.1145/1216295.1216307]
• 18: B. Mobasher, R. Burke, C. Williams, and R. Bhaumik. Analysis and detection of segment-focused attacks against collaborative recommendation. 2006.
• 19: B. Mobasher, R. D. Burke, and J. J. Sandvig. Model-based collaborative filtering as a defense against profile injection attacks. In AAAI, 2006.
• 20: Michael O'Mahony , Neil Hurley , Nicholas Kushmerick , Guénolé Silvestre, Collaborative recommendation: A robustness analysis, ACM Transactions on Internet Technology (TOIT), v.4 n.4, p.344-377, November 2004 [doi>10.1145/1031114.1031116]
• 21: Michael P. O'Mahony , Neil J. Hurley , Guénolé C.M. Silvestre, Detecting noise in recommender system databases, Proceedings of the 11th international conference on Intelligent user interfaces, January 29-February 01, 2006, Sydney, Australia [doi>10.1145/1111449.1111477]
• 22: T. D. Sanger. Optimal Unsupervised Learning in a single-layer linear feedforward neural network. Neural Networks, 2(6):459--473, 1989.
• 23: B. Sarwar, G. Karypis, J. Konstan, and J. Riedl. Application of dimensionality reduction in recommender systems - a case study. Defense Technical Information Center, 2000.
• 24: B. Webb. Netflix update: Try this at home. http://sifter.org/~simon/journal/20061211.html, 2006.
• 25: C. Williams, B. Mobasher, R. Burke, J. Sandvig, and R. Bhaumik. Detection of Obfuscated Attacks in Collaborative Recommender Systems. In Workshop on Recommender Systems, ECAI, 2006.
• 26: Sheng Zhang , Weihong Wang , James Ford , Fillia Makedon , Justin Pearlman, Using Singular Value Decomposition Approximation for Collaborative Filtering, Proceedings of the Seventh IEEE International Conference on E-Commerce Technology, p.257-264, July 19-22, 2005 [doi>10.1109/ICECT.2005.102]

INDEX TERMS

Primary Classification:
  G. Mathematics of Computing
  G.3 PROBABILITY AND STATISTICS
      Subjects: Robust regression

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval

General Terms:
Algorithms