A large-scale and fault-tolerant approach of subgraph mining using density-based partitioning

TL;DR

This paper presents a scalable, fault-tolerant subgraph mining method using density-based partitioning within the MapReduce framework, significantly reducing execution time on large graph databases.

Contribution

It introduces a novel density-based partitioning technique for subgraph mining that enhances scalability and fault tolerance in large distributed environments.

Findings

Decreases execution time significantly

Scales subgraph discovery to large databases

Balances computational load effectively

Abstract

Recently, graph mining approaches have become very popular, especially in domains such as bioinformatics, chemoinformatics and social networks. In this scope, one of the most challenging tasks is frequent subgraph discovery. This task has been motivated by the tremendously increasing size of existing graph databases. Since then, an important problem of designing efficient and scaling approaches for frequent subgraph discovery in large clusters, has taken place. However, failures are a norm rather than being an exception in large clusters. In this context, the MapReduce framework was designed so that node failures are automatically handled by the framework. In this paper, we propose a large-scale and fault-tolerant approach of subgraph mining by means of a density-based partitioning technique, using MapReduce. Our partitioning aims to balance computation load on a collection of machines. We experimentally show that our approach decreases significantly the execution time and scales the subgraph discovery process to large graph databases.