Search Results for "frequent subgraph mining"

When data mining techniques are applied to discover useful knowledge behind a large data collection, they are required to be able to preserve some confidential information, such as sensitive frequent itemsets, rules and the like. A feasible way to ensure the confidentiality is to sanitize the database and conceal sensitive information. However, the sanitization process often produces side effects, thus minimizing these side effects is an important task.

This project aims to develop and share fast frequent subgraph mining and graph learning algorithms. Currently we release the frequent subgraph mining package FFSM and later we will include new functions for graph regression and classification package

Incremental data mining algorithms process frequent up- dates to dynamic datasets efficiently by avoiding redundant computa- tion. Existing incremental extension to shared nearest neighbor density based clustering (SNND) algorithm cannot handle deletions to dataset and handles insertions only one point at a time. We present an incremen- tal algorithm to overcome both these bottlenecks by efficiently identify- ing affected parts of clusters while processing updates to dataset in batch mode.

This is the program used in the following paper: Wenqing Lin, Xiaokui Xiao, and Gabriel Ghinita. Large-Scale Frequent Subgraph Mining in MapReduce. In Proceedings of the 30th IEEE International Conference on Data Engineering (ICDE), pages 844-855, 2014. Please cite the paper if you choose to use the program. If having any problems, please report to {wlin1 at ntu dot edu dot sg}.

The Apriori Algorithm is an influential algorithm for mining frequent itemsets for boolean association rules. Key Concepts : • Frequent Itemsets: The sets of item which has minimum support (denoted by Li for i th -Itemset). • Apriori Property: Any subset of frequent itemset must be frequent. • Join Operation: To find Lk , a set of candidate k-itemsets is generated by joining Lk-1 with itself.

We propose a parallel algorithm to do representative approximate frequent subgraph mining based on the REAFUM algorithm in this project. We successfully apply Fork-Join Model to our algorithm and parallelize the calculations on the generation of graph mapping distance matrix. Our algorithm guarantees identical results with REAFUM given same input while achieving significant improvements in runtime when running with multi-threads. We also demonstrate the scalability of our algorithm...

This is an optimized Java implementation of the algorithm from "LTS: Discriminative Subgraph Mining by Learning from Search History" in Data Engineering (ICDE), IEEE 27th International Conference, pages 207-218, 2011. The Learning to Search (LTS) algorithm mines for discriminative subgraphs. Given two sets of graphs, with one set labelled positive, it finds subgraphs that are common in the positive graphs and uncommon in the negative graphs. In other words, the occurrences of these subgraphs...

..., the total worst-case algorithm complexity is O(m^n * n(n-1)/2 * km * log m). This Java implementation implements our ASM algorithm. See README file: https://sourceforge.net/projects/asmalgorithm/files/ If you use our ASM implementation to support academic research, please cite the following paper: Haibin Liu, Lawrence Hunter, Vlado Keselj, and Karin Verspoor. Approximate Subgraph Matching-based Literature Mining for Biomedical Events and Relations. PLOS ONE, 8:4 e60954, 2013.

In this project, we tackle the calculation of frequent items in a data stream, and show how it can be implemented using GPUs.

LTS (Learning to Search) is an implementation of an algorithm described in "LTS: Discriminative Subgraph Mining by Learning from Search History" in Data Engineering (ICDE), IEEE 27th International Conference, pages 207-218, 2011. The purpose of LTS is to find discriminative subgraphs, which are smaller graphs that are embedded in larger graphs that all share a certain trait. A discriminative subgraph can help to characterize a complex graph and can be used to classify new graphs with unknown...

implementation of "GAIA: graph classification using evolutionary computation" in SIGMOD'10. a discriminative subgraph pattern mining algorithm using evolutionary computation implemented by the author

This open source project is aimed to create an efficient XML frequent pattern mining tool,which includes four main functions, TreeMining, Stream Mining, Sequence Mining and Version Mining.

A data mining tool for finding frequent motifs in DNA regulatory area that may play significant role in gene regulation. It makes the search more efficient by using different data like conservation and binding scores about relevant promoter areas. It is implemented as a part of Barchelor thesis work of Timo Petmanson available here: http://comserv.cs.ut.ee/forms/ati_report/downloader.php?file=0701eb033c3bad8d3be4a79a29c70107c1cad745

This project aims to create a method able to determine the most frequent word phrases in a large source of text data (>5 Gb) using the computational power of multiple processors.

It is the source code for a tree mining algorithm called TRIPS. It can mine frequent subtrees from a forest of tree structures.

Data mining tool for the extraction of spatio-temporal frequent patterns ("Trajectory patterns" or "T-patterns") from GPS-like trajectories of a set of moving objects. Work performed within the European project GeoPKDD - www.geopkdd.eu

baobab is an implementation of FPTrees or Frequent Pattern Trees, a pattern recognition/data mining technique. it has innumerable applications in language processing, clickstream analysis, etc.

DMTL (Data Mining Template Library) - A generic C++ based library for mining structured patterns such as sets, sequences, trees and graphs. The library provides implementation of popular frequent pattern mining algorithms.

This project implements the algorithm proposed in page 109-118, ACM SIGKDD, 2003, "Inverted matrix: efficient discovery of frequent items in large datasets in the context of interactive mining" and its improvements.