Improving On-Demand Learning to Rank through Parallelism

Sousa, Daniel Xavier; Rosa, Thierson Couto; Martins, Wellington Santos; Silva, Rodrigo; Gonçalves, Marcos André

doi:10.1007/978-3-642-35063-4_38

Cited by 4 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different from the eager methods, lazy methods build the ranking model only after the new query is obtained, providing a customized model for the query, at the cost of creating a ranking model for each new query. As far as we know, the work of De Sousa et al is the only L2R proposal similar to ours. The authors propose a parallel version of the LRAR algorithm, called PLRAR, that runs on a GPU, and make use of a reduced training dataset but using a serial implementation of SSARP .…”

Section: Related Work and Backgroundsupporting

confidence: 73%

Parallel rule‐based selective sampling and on‐demand learning to rank

Freitas

Sousa

Martins

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary Learning to rank (L2R) works by constructing a ranking model from training data so that, given a new query, the model is able to generate an effective rank of the objects for the query. Almost all work in L2R focus on ranking accuracy leaving performance and scalability overlooked. However, performance is a critical factor, especially when dealing with on‐demand queries. In this scenario, Learning to Rank using association rules has been shown to be extremely effective but only at a high computational cost. In this work, we show how to exploit parallelism on rule‐based systems to: i) drastically reduce L2R training datasets using selective sampling and ii) to generate query customized ranking models on the fly. We present parallel algorithms and GPU implementations for these two tasks showing that dataset reduction takes only a few seconds with speedups up to 148x over a serial baseline, and that queries can be processed in only a few milliseconds with speedups of 1000x over a serial baseline and 29x over a parallel baseline for the best case. We also extend the implementations to work with multiple GPUs, further increasing the speedup over the baselines and showing the scalability of our proposed algorithms.

show abstract

Section: Related Work and Backgroundsupporting

confidence: 73%

Parallel rule‐based selective sampling and on‐demand learning to rank

Freitas

Sousa

Martins

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…However, the use of parallelism in L2R has focused on accelerating the training phase of standard solutions, i.e., those based on a batch strategy. The work in [De Sousa et al 2012] is the only one, as far as we know, that supports on demand learning to rank, similarly to our proposal.…”

Section: Related Worksupporting

confidence: 71%

“…However, almost none of these studies targeted the L2R sub-field of information retrieval. With the growing importance of the subject, some researchers have proposed efficient L2R through the use of parallel processing [Shukla et al 2012, Wang et al 2015, Jin et al 2015, De Sousa et al 2012]. However, the use of parallelism in L2R has focused on accelerating the training phase of standard solutions, i.e., those based on a batch strategy.…”

Section: Related Workmentioning

confidence: 99%

A Fast and Scalable Manycore Implementation for an On-Demand Learning to Rank Method

Freitas¹,

Sousa²,

Martins³

et al. 2016

Anais Do XVII Simpósio Em Sistemas Computacionais De Alto Desempenho (SSCAD 2016)

Self Cite

View full text Add to dashboard Cite

Learning to rank (L2R) works by constructing a ranking model from training data so that, given unseen data (query), a somewhat similar ranking is produced. Almost all work in L2R focuses on ranking accuracy leaving performance and scalability overlooked. In this work we present a fast and scalable manycore (GPU) implementation for an on-demand L2R technique that builds ranking models on the ﬂy. Our experiments show that we are able to process a query (build a model and rank) in only a few milliseconds, achieving a speedup of 508x over a serial baseline and 4x over a parallel baseline for the best case. We extend the implementation to work with multiple GPUs, further increasing the speedup over the parallel baseline to approximately x16 when using 4 GPUs.

show abstract

“…During the dissertation, we published some papers in the world leading In-formation Retrieval conferences and journals, such as [Sousa et al 2016](A1) and [Sousa et al 2019](A2). Beside them, we also published other papers in L2R area, as [Sousa et al 2012](B1), [Freitas et al 2016](B3) 3 , and [Freitas et al 2018](A2).…”

Section: Research Goalsmentioning

confidence: 99%

Evolutionary Risk-Sensitive Feature Selection for Learning to Rank

Sousa¹

2019

Anais Do Concurso De Teses E Dissertações Da SBC (CTD-SBC)

Self Cite

View full text Add to dashboard Cite

Learning to Rank (L2R) is one of the main research lines in Information Retrieval. Risk-sensitive L2R is a sub-area of L2R that tries to learn models that are good on average while at the same time reduce the risk of performing poorly in a few but important queries (e.g., medical or legal queries). One way of reducing risk in learned models is by selecting and removing noisy, redundant or features that promote some queries in detriment of others. This is exacerbated by learning methods that usually maximize an average metric (e.g., mean average precision (MAP) or Normalized Discounted Cumulative Gain (NDCG)). However, historically feature selection (FS) methods have focused only on effectiveness and feature reduction as the main objectives. Accordingly, in this work we propose to evaluate FS for L2R with an additional objective in mind, namely risk-sensitiveness. We present novel single and multi-objective criteria to optimize feature reduction, effectiveness and risk-sensitiveness, all at the same time. We also introduce a new methodology to explore the search space, suggesting effective and efficient extensions of a well-known Evolutionary Algorithm (SPEA2) for FS applied to L2R. Our experiments show that explicitly including risk as an objective criterion is crucial to achieve more effective and risk-sensitive performance. We also provide a thorough analysis of our methodology and experimental results.

show abstract

Improving On-Demand Learning to Rank through Parallelism

Cited by 4 publications

References 12 publications

Parallel rule‐based selective sampling and on‐demand learning to rank

Parallel rule‐based selective sampling and on‐demand learning to rank

A Fast and Scalable Manycore Implementation for an On-Demand Learning to Rank Method

Evolutionary Risk-Sensitive Feature Selection for Learning to Rank

Contact Info

Product

Resources

About