Discovering closed frequent itemsets on multicore: Parallelizing computations and optimizing memory accesses

Négrevergne, Benjamin; Termier, Alexandre; Méhaut, Jean‐François; Uno, Takeaki

doi:10.1109/hpcs.2010.5547082

Cited by 31 publications

(24 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have already shown that the set systems corresponding to a set of patterns defined with a monotone constraint, with a convertible anti-monotone constraint or with a loose anti-monotone constraint (Negrevergne, 2011) is partially accessible. Studying the connection between accessibility properties and constraint based pattern mining opens some important research perspectives that will be discussed in Section 8.…”

Section: Connections Between Constraints and Accessibility Propertiesmentioning

confidence: 99%

“…The task decomposition in ParaMiner is recursive, which allows larger tasks to be decomposed in sub-tasks. In previous work (Negrevergne, 2011) we conducted experiments that demonstrated that load imbalance was not an issue in ParaMiner.…”

Section: Parallel Pattern Miningmentioning

confidence: 99%

“…Ghoting et al (2005) have shown that pattern mining algorithms generally perform more accesses to the memory than others which put too much pressure on the bus connecting memory and computing cores (Tatikonda and Parthasarathy, 2009). In addition, traditional optimizations tend to worsen to problem (Negrevergne et al, 2010) because they only reduce the amount of computation required and not the amount of data transfers. This problem can be solved by performing deep changes in the algorithms to reduce data transfers generally at the cost of an additional computations.…”

Section: Parallel Pattern Miningmentioning

confidence: 99%

“…We first compare the execution times necessary to mine closed frequent itemsets. In this experiment ParaMiner is compared with the stateof-the-art parallel ad-hoc algorithms PLCM (Negrevergne et al, 2010) and MT-Closed . These algorithm are parallel implementations of the two fastest algorithm according to the FIMI workshop (Goethals, 2004).…”

Section: Algorithmmentioning

confidence: 99%

See 3 more Smart Citations

Para Miner: a generic pattern mining algorithm for multi-core architectures

Négrevergne

Termier

Rousset

et al. 2013

Data Min Knowl Disc

View full text Add to dashboard Cite

In this paper, we present ParaMiner which is a generic and parallel algorithm for closed pattern mining.ParaMiner is built on the principles of pattern enumeration in strongly accessible set systems. Its efficiency is due to a novel dataset reduction technique (that we call EL-reduction), combined with novel technique for performing dataset reduction in a parallel execution on a multi-core architecture.We illustrate ParaMiner's genericity by using this algorithm to solve three different pattern mining problems: the frequent itemset mining problem, the mining frequent connected relational graphs problem and the mining gradual itemsets problem.In this paper, we prove the soundness and the completeness of ParaMiner. Furthermore, our experiments show that despite being a generic algorithm, ParaMiner can compete with specialized state of the art algorithms designed for the pattern mining problems mentioned above. Besides, for the particular problem of gradual itemset mining, ParaMiner outperforms the state of the art algorithm by two orders of magnitude.

show abstract

Section: Connections Between Constraints and Accessibility Propertiesmentioning

confidence: 99%

Section: Parallel Pattern Miningmentioning

confidence: 99%

Section: Parallel Pattern Miningmentioning

confidence: 99%

Section: Algorithmmentioning

confidence: 99%

See 2 more Smart Citations

Para Miner: a generic pattern mining algorithm for multi-core architectures

Négrevergne

Termier

Rousset

et al. 2013

Data Min Knowl Disc

View full text Add to dashboard Cite

show abstract

“…Hence 10 cannot be pruned: although it yields an useless CIS, one of its extensions leads to a useful one (step 12 ). In this tree we can only prune the recursion towards step 11 . This example's distribution is unbalanced in order to show TopPI's corner cases with only 4 items; but in real datasets, with hundreds of thousands of items, such cases regularly occur.…”

Section: Finding Pruning Opportunities In An Example Enumerationmentioning

confidence: 99%

TopPI: An Efficient Algorithm for Item-Centric Mining

Kirchgessner

Leroy

Termier

et al. 2016

Big Data Analytics and Knowledge Discovery

View full text Add to dashboard Cite

Abstract. We introduce TopPI, a new semantics and algorithm designed to mine long-tailed datasets. For each item, and regardless of its frequency, TopPI finds the k most frequent closed itemsets that item belongs to. For example, in our retail dataset, TopPI finds the itemset "nori seaweed, wasabi, sushi rice, soy sauce" that occurrs in only 133 store receipts out of 290 million. It also finds the itemset "milk, puff pastry", that appears 152,991 times. Thanks to a dynamic threshold adjustment and an adequate pruning strategy, TopPI efficiently traverses the relevant parts of the search space and can be parallelized on multi-cores. Our experiments on datasets with different characteristics show the high performance of TopPI and its superiority when compared to state-of-the-art mining algorithms. We show experimentally on real datasets that TopPI allows the analyst to explore and discover valuable itemsets.

show abstract

A Parallel Strategy for the Logical‐probabilistic Calculus‐based Method to Calculate Two‐terminal Reliability

Nguyen

2015

Quality & Reliability Eng

View full text Add to dashboard Cite

The theory of network reliability has been applied to many complicated network structures, such as computer and communication networks, piping systems, electricity networks, and traffic networks. The theory is used to evaluate the operational performance of networks that can be modeled by probabilistic graphs. Although evaluating network reliability is an Non-deterministic Polynomial-time hard problem, numerous solutions have been proposed. However, most of them are based on sequential computing, which under-utilizes the benefits of multi-core processor architectures. This paper addresses this limitation by proposing an efficient strategy for calculating the two-terminal (terminal-pair) reliability of a binary-state network that uses parallel computing. Existing methods are analyzed. Then, an efficient method for calculating terminal-pair reliability based on logical-probabilistic calculus is proposed. Finally, a parallel version of the proposed algorithm is developed. This is the first study to implement an algorithm for estimating terminal-pair reliability in parallel on multicore processor architectures. The experimental results show that the proposed algorithm and its parallel version outperform an existing sequential algorithm in terms of execution time.

show abstract

Discovering closed frequent itemsets on multicore: Parallelizing computations and optimizing memory accesses

Cited by 31 publications

References 10 publications

Para Miner: a generic pattern mining algorithm for multi-core architectures

Para Miner: a generic pattern mining algorithm for multi-core architectures

TopPI: An Efficient Algorithm for Item-Centric Mining

A Parallel Strategy for the Logical‐probabilistic Calculus‐based Method to Calculate Two‐terminal Reliability

Contact Info

Product

Resources

About