PARASOL: a hybrid approximation approach for scalable frequent itemset mining in streaming data

Abstract

Here, we present a novel algorithm for frequent itemset mining in streaming data (FIM-SD). For the past decade, various FIM-SD methods in one-pass approximation settings that allow to approximate the support of each itemset have been proposed. They can be categorized into two approximation types: parameter-constrained (PC) mining and resource-constrained (RC) mining. PC methods control the maximum error that can be included in the approximate support based on a pre-defined parameter. In contrast, RC methods limit the maximum memory consumption based on resource constraints. However, the existing PC methods can exponentially increase the memory consumption, while the existing RC methods can rapidly increase the maximum error. In this study, we address this problem by introducing a hybrid approach of PC-RC approximations, called PARASOL. For any streaming data, PARASOL ensures to provide a condensed representation, called a-covered set, which is regarded as an extension of the closedness compression; when = 0, the solution corresponds to the ordinary closed itemsets. PARASOL searches for such approximate closed itemsets that can restore the frequent itemsets and their supports while the maximum error is bounded by an integer,. Then, we empirically demonstrate that the proposed algorithm significantly outperforms the state-of-the-art PC and RC methods for FIM-SD.

A multithreaded hybrid framework for mining frequent itemsets

“…This framework however has not done enough investigation on exploring the criteria for switching between both the algorithms. A hybrid framework PARASOL comprising of the combination of resource-constrained mining and parameter constrained mining was presented by Yamamoto et al [13]. The former sets a limit to memory consumption while the latter controls the error rate.…”

CICLAD: A Fast and Memory-efficient Closed Itemset Miner for Streams

“…Both task are challenging due to the specific conditions of the stream environment: dynamic data inflow, potential concept drift and, typically, limited resources [12,26]. Therefore, the design of efficient stream miners has to reflect concerns such as single access to stream data, compact storage of results, resource limit-awareness, etc.…”