GPU acceleration of probabilistic frequent itemset mining from uncertain databases

Kozawa, Yusuke; Amagasa, Toshiyuki; Kitagawa, Hiroyuki

doi:10.1145/2396761.2396874

Cited by 7 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first show the result of whole algorithms and then analyze the several aspects of the algorithms in detail. Figures 2(a)-2(c) show the speedups of the three methods compared to the single-GPU method [9], with varying minsup values. We measured execution time as elapsed time from when the dataset is ready on CPU to when all the result are collected to CPU.…”

Section: Results On a Single Nodementioning

confidence: 99%

“…The single-GPU method [9] follows the pApriori algorithm and consists of generating candidates and extracting PFIs. Candidates are generated on a GPU by a parallel version of the algorithm described in Sect.…”

Section: Single-gpu Parallelizationmentioning

confidence: 99%

“…Then PFIs are extracted with four steps: inclusion check, pruning, filtering, and computing SPMFs. For more details, readers are encouraged to refer to the paper [9].…”

Section: Single-gpu Parallelizationmentioning

confidence: 99%

“…In addition, because the GPU architecture is relatively simpler than the CPU architecture, GPUs have been evolving rapidly [20]. By leveraging such a promising processor, our previous work [9] accelerated an algorithm of probabilistic frequent itemset mining. Meanwhile, GPU clusters, which are computer clusters where each node has one or more GPUs, have emerged as a powerful computing platform, such as HA-PACS, * TSUBAME2.0, * * and Titan.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Probabilistic Frequent Itemset Mining on a GPU Cluster

Kozawa

Amagasa

Kitagawa

2014

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYProbabilistic frequent itemset mining, which discovers frequent itemsets from uncertain data, has attracted much attention due to inherent uncertainty in the real world. Many algorithms have been proposed to tackle this problem, but their performance is not satisfactory because handling uncertainty incurs high processing cost. To accelerate such computation, we utilize GPUs (Graphics Processing Units). Our previous work accelerated an existing algorithm with a single GPU. In this paper, we extend the work to employ multiple GPUs. Proposed methods minimize the amount of data that need to be communicated among GPUs, and achieve load balancing as well. Based on the methods, we also present algorithms on a GPU cluster. Experiments show that the single-node methods realize near-linear speedups, and the methods on a GPU cluster of eight nodes achieve up to a 7.1 times speedup.

show abstract

Section: Results On a Single Nodementioning

confidence: 99%

Section: Single-gpu Parallelizationmentioning

confidence: 99%

“…Then PFIs are extracted with four steps: inclusion check, pruning, filtering, and computing SPMFs. For more details, readers are encouraged to refer to the paper [9].…”

Section: Single-gpu Parallelizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Probabilistic Frequent Itemset Mining on a GPU Cluster

Kozawa

Amagasa

Kitagawa

2014

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…We now present the experimental results on two datasets that have been used in recent related work, for example [6,25,43]. The second dataset, called T10I4D100k, is produced by the IBM data generator.…”

Section: Resultsmentioning

confidence: 99%

Model-based probabilistic frequent itemset mining

et al. 2012

View full text Add to dashboard Cite

Data uncertainty is inherent in emerging applications such as location-based services, sensor monitoring systems, and data integration. To handle a large amount of imprecise information, uncertain databases have been recently developed. In this paper, we study how to efficiently discover frequent itemsets from large uncertain databases, interpreted under the Possible World Semantics. This is technically challenging, since an uncertain database induces an exponential number of possible worlds. To tackle this problem, we propose a novel methods to capture the itemset mining process as a probability distribution function taking two models into account: the Poisson distribution and the normal distribution. These model-based approaches extract frequent itemsets with a high degree of accuracy and support large databases. We apply our techniques to improve the performance of the algorithms for (1) finding itemsets whose frequentness probabilities are larger than some threshold and (2) mining itemsets with the k highest frequentness probabilities. Our approaches support both tuple and attribute uncertainty models, which are commonly used to represent uncertain databases. Extensive evaluation on real and synthetic datasets shows that our methods are highly accurate and four orders of magnitudes faster than previous approaches. In further theoretical and experimental studies, we give an intuition which model-based approach fits best to different types of data sets.

show abstract