A subgraph mining algorithm on big data
- 1 December 2016
Abstract
Frequent subgraph mining (FSM) may be a crucial task for beta data analysis on graph data. Over the years, several algorithms area unit planned to resolve this task. These algorithms assume that the knowledge structure of the mining task is tiny enough to suit inside the most memory of a computer. However, as a result of the real-world graph data grows, every in size and quantity, such academic degree assumption does not hold from currently on. To beat this, some graph database-centric ways in which area unit planned in recent years for determination FSM; FSM algorithmic program on this paradigm is of giant demand. The first dataset is split into fragments, then every fragment is mined on an individual basis and therefore the results area unit combined along to generate a worldwide result. One in every of the difficult problems in graph mining is concerning the completeness because the of complexness graph structures. we'll prove the completeness of our algorithmic program during this paper. The experiments are conducted as an example the potency of our information partitioning approach.Keywords
This publication has 8 references indexed in Scilit:
- MuppetProceedings of the VLDB Endowment, 2012
- Spectral Analysis for Billion-Scale Graphs: Discoveries and ImplementationLecture Notes in Computer Science, 2011
- Large-Scale Social Network Analysis Based on MapReducePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Cloud computing: A new business paradigm for biomedical information sharingJournal of Biomedical Informatics, 2010
- PEGASUS: A Peta-Scale Graph Mining System Implementation and ObservationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- MapReduceCommunications of the ACM, 2008
- Using and Learning Semantics in Frequent Subgraph MiningLecture Notes in Computer Science, 2006
- Mining protein family specific residue packing patterns from protein structure graphsPublished by Association for Computing Machinery (ACM) ,2004