Abstract
Traditional Learning to Rank (L2R) is usually conducted in a batch mode in which a single ranking function is learned to order results for future queries. This approach is not flexible since future queries may differ considerably from those present in the training set and, consequently, the learned function may not work properly. Ideally, a distinct learning function should be learned on demand for each query. Nevertheless, on-demand L2R may significantly degrade the query processing time, as the ranking function has to be learned on-the-fly before it can be applied. In this paper we present a parallel implementation of an on-demand L2R technique that reduces drastically the response time of previous serial implementation. Our implementation makes use of thousands of threads of a GPU to learn a ranking function for each query, and takes advantage of a reduced training set obtained through active learning. Experiments with the LETOR benchmark show that our proposed approach achieves a mean speedup of 127x in query processing time when compared to the sequential version, while producing very competitive ranking effectiveness.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Agrawal, R., Imieliński, T., Swami, A.: Mining association rules between sets of items in large databases. In: Proceedings of the 1993 ACM SIGMOD International Conference on Management of Data, SIGMOD 1993, pp. 207–216. ACM, New York (1993)
Barroso, L.A., Dean, J., Hölzle, U.: Web search for a planet: The google cluster architecture. IEEE Micro. 23(2), 22–28 (2003)
Burges, C., Shaked, T., Renshaw, E., Lazier, A., Deeds, M., Hamilton, N., Hullender, G.: Learning to rank using gradient descent. In: Proceedings of the 22nd International Conference on Machine Learning, ICML 2005, pp. 89–96. ACM, New York (2005)
Chapelle, O., Chang, Y., Liu, T.-Y.: Future directions in learning to rank. Journal of Machine Learning Research - Proceedings Track 14, 91–100 (2011)
Clarke, C.L.A., Terra, E.L.: Approximating the top-m passages in a parallel question answering system. In: Proceedings of the Thirteenth ACM International Conference on Information and Knowledge Management, CIKM 2004, pp. 454–462. ACM, New York (2004)
de Almeida, H.M., Gonçalves, M.A., Cristo, M., Calado, P.: A combined component approach for finding collection-adapted ranking functions based on genetic programming. In: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2007, pp. 399–406. ACM, New York (2007)
Ding, S., He, J., Yan, H., Suel, T.: Using graphics processors for high-performance ir query processing. In: Proceedings of the 17th International Conference on World Wide Web, WWW 2008, pp. 1213–1214. ACM, New York (2008)
Qin, T., Liu, T.-Y., Xu, J., Li, H.: Letor: A benchmark collection for research on learning to rank for information retrieval. Inf. Retr. 13, 346–374 (2010)
Silva, R., Gonçalves, M.A., Veloso, A.: Rule-Based Active Sampling for Learning to Rank. In: Gunopulos, D., Hofmann, T., Malerba, D., Vazirgiannis, M. (eds.) ECML PKDD 2011, Part III. LNCS, vol. 6913, pp. 240–255. Springer, Heidelberg (2011)
Teodoro, G., Mariano, N., Meira Jr., W., Ferreira, R.: Tree projection-based frequent itemset mining on multicore cpus and gpus. In: Proceedings of the 2010 22nd International Symposium on Computer Architecture and High Performance Computing, SBAC-PAD 2010, pp. 47–54. IEEE Computer Society, Washington, DC (2010)
Tyree, S., Weinberger, K.Q., Agrawal, K., Paykin, J.: Parallel boosted regression trees for web search ranking. In: Proceedings of the 20th International Conference on World Wide Web, WWW 2011, pp. 387–396. ACM, New York (2011)
Veloso, A.A., Almeida, H.M., Gonçalves, M.A., Meira Jr., W.: Learning to rank at query-time using association rules. In: Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2008, pp. 267–274. ACM, New York (2008)
Wang, B., Wu, T., Yan, F., Li, R., Xu, N., Wang, Y.: Rankboost acceleration on both nvidia cuda and ati stream platforms. In: Proceedings of the 2009 15th International Conference on Parallel and Distributed Systems, ICPADS 2009, pp. 284–291. IEEE Computer Society, Washington, DC (2009)
Wang, S., Gao, B.J., Wang, K., Lauw, H.W.: Parallel learning to rank for information retrieval. In: Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2011, pp. 1083–1084. ACM, New York (2011)
Wei, Z., JaJa, J.: A fast algorithm for constructing inverted files on heterogeneous platforms. In: Proceedings of the 2011 IEEE International Parallel & Distributed Processing Symposium, IPDPS 2011, pp. 1124–1134. IEEE Computer Society, Washington, DC (2011)
Yue, Y., Finley, T., Radlinski, F., Joachims, T.: A support vector method for optimizing average precision. In: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2007, pp. 271–278. ACM, New York (2007)
Zhang, F., Zhang, Y., Bakos, J.: Gpapriori: Gpu-accelerated frequent itemset mining. In: Proceedings of the 2011 IEEE International Conference on Cluster Computing, CLUSTER 2011, pp. 590–594. IEEE Computer Society, Washington, DC (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
De Sousa, D.X., Rosa, T.C., Martins, W.S., Silva, R., Gonçalves, M.A. (2012). Improving On-Demand Learning to Rank through Parallelism. In: Wang, X.S., Cruz, I., Delis, A., Huang, G. (eds) Web Information Systems Engineering - WISE 2012. WISE 2012. Lecture Notes in Computer Science, vol 7651. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35063-4_38
Download citation
DOI: https://doi.org/10.1007/978-3-642-35063-4_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35062-7
Online ISBN: 978-3-642-35063-4
eBook Packages: Computer ScienceComputer Science (R0)