一种局部协同过滤的排名推荐算法

doi:10.6040/j.issn.1672-3961.2.2015.008

摘要/Abstract

摘要： 基于矩阵分解模型、时间因素和排名模式,提出一种局部协同过滤的排名推荐算法,并放松用户对项目的评分矩阵是低秩的这一假设,假设用户对项目的评分矩阵是局部低秩的,即评分矩阵在某个用户项目序偶的近邻空间内是低秩的。修改信息检索中常用的评价指标平均倒数排名(mean reciprocal rank, MRR)函数,使其适合评分数据集合,然后对其进行平滑化操作和简化操作,最后直接优化这一评价指标。提出的算法易于并行化,可以在大型的真实数据集合上运行。试验结果表明该算法能提升推荐的性能。

关键词: 推荐系统, 协同过滤, 时间因素, 平均倒数排名, 矩阵分解

Abstract: Based on matrix factorization model, time factor and ranking problem, a collaborative filtering algorithm was proposed. The method relaxed the low-rank assumption of rating matrix and assumed that the rating matrix was locally low-rank,which meaned that the rating matrix was low-rank in the neighborhood of certain user-item combination. Mean reciprocal rank(MRR), an evaluation metric widely used in Information retrieval, was modified to fit the rating dataset. The evaluation metric was smoothed and simplied, and then was optimized. The algorithm was easy to parallelize and could operate on real data set. Experiments showed that this algorithm could improve recommendation performance.

Key words: time factor, matrix factorization, mean reciprocal rank, recommendation system, collaborative filtering

中图分类号:

TP181

黄丹,王志海,刘海洋. 一种局部协同过滤的排名推荐算法[J]. 山东大学学报(工学版), 2016, 46(5): 29-36.

HUANG Dan, WANG Zhihai, LIU Haiyang. A local collaborative filtering algorithm based on ranking recommendation tasks[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2016, 46(5): 29-36.

参考文献

[1] LYU L Y, MEDO M, YEUNG C H, et al. Recommender systems[J]. The Journal of Physics Reports, 2012, 519(1):1-50.
[2] RICCI F, ROKACH L, SHAPIRA B, et al. Recommender systems handbook[M]. Berlin, Germany: Springer-Verlag, 2011.
[3] LEE D, SEUNG H. Algorithms for non-negative matrix factorization[J]. Advances in Neural Information Processing System, 2001, 32(6):556-562.
[4] SALAKHUTDINOV R, MNIH A. Probabilistic matrix factorization[J]. Advances in Neural Information Processing Systems, 2012:1257-1264.
[5] SALAKHUTDINOV R, MNIH A. Bayesian probabilistic matrix factorization using markov chain monte carlo[C] // Proceedings of the 25th International Conference on Machine Learning. New York, USA: ACM, 2008:880-887.
[6] LEE J, KIM S, LEBANON G, et al. Local low-rank matrix approximation[J]. Journal of Machine Learning Research, 2013, 28(2):82-90.
[7] KOREN Y. Factor in the neighbors: Scalable and accurate collaborative filtering[J]. ACM Transactions on Knowledge Discovery from Data, 2010, 4(1):1-24.
[8] CREMONESI P, KOREN Y, TURRIN R. Performance of recommender algorithms on top-n recommendation tasks[C] //Proceedings of the fourth ACM Conference on Recommender Systems. New York, USA: ACM, 2013:39-46.
[9] DING Y, LI X. Time weight collaborative filtering[C] //Proceedings of the 14^th ACM International Conference on Information and Knowledge Management. New York, USA: ACM, 2005:485-492.
[10] GONG S J, CHENG G H. Mining user interest change for improving collaborative filtering[C] //Proceedings of the 2008 Second International Symposium on Intelligent Information Technology Application. Washington DC, USA: IEEE Computer Society, 2008:24-27.
[11] LEE T Q, PARK Y, PARK Y T. A time-based approach to effective recommender systems using implicit feedback[J]. Expert Systems with Applications, 2008, 34(4): 3055-3062.
[12] BURGES C, SHAKED T, RENSHAW E, et al. Learning to rank using gradient descent[C] //Proceedings of the 22^nd International Conference on Machine Learning. New York, USA: ACM, 2005:89-96.
[13] RENDLE S, FREUDENTHALER C. Improving pairwise learning for item recommendation from implicit feedback[C] //Proceedings of the 7th ACM International Conference on Web Search and Cata Mining. New York, USA: ACM, 2014:273-282.
[14] CAO Z, QIN T, LIU T Y, et al. Learning to rank: from pairwise approach to listwise approach[C] //Proceedings of the 24^th International Conference on Machine Learning. New York, USA: ACM, 2007:129-136.
[15] XU J, LIU T Y, LU M, et al. Directly optimizing evaluation measures in learning to rank[C] //Proceedings of the 31^st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2008: 107-114.
[16] WEIMER M, KARATZOGLOU A, LE Q V, et al. CofiRank-maximum margin matrix factorization for collaborative ranking[C] //Neural Information Processing Systems. Vancouver, Canada: ACM, 2007:3-8.
[17] SHI Y, KARATZOGLOU A, BALTRUNAS L, et al. TFMAP: optimizing map for top-n context-aware recommendation[C] //Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2012:155-164.
[18] SHI Y, KARATZOGLOU A, BALTRUNAS L, et al. CLIMF: learning to maximize reciprocal rank with collaborative less-is-more filtering[C] //Proceedings of the Sixth ACM Conference on Recommender Systems. New York, USA: ACM, 2012:139-146.
[19] KABBUR S, XIA N, KARYPIS G. FISM: factored item similarity models for top-N recommender systems[C] //Proceedings of the 19^th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2010: 659-667.
[20] GROUPLENS. Datasets Instruction[EB/OL]. [2015-04-15]. http://grouplens.org/datasets/movielens.
[21] LEE J, SUN M, LEBANON G. PREA [EB/OL].(2013-06-13)[2015-04-10]. http://prea.gatech.edu/download.html#ver20.
[22] LEE J, SUN M, LEBANON G. PREA: personalized recommendation algorithms toolkit[J]. The Journal of Machine Learning Research, 2012, 13(1):2699-2703.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed