Efficient mining of frequent subgraphs in the presence of isomorphism

Huan, Jun; Wang, W.; Prins, Jan F.

doi:10.1109/icdm.2003.1250974

Cited by 418 publications

(401 citation statements)

References 8 publications

Supporting

Mentioning

397

Contrasting

Unclassified

Order By: Relevance

“…UML and ER diagrams are other examples. There has been a considerable effort, from both database and data mining communities, in developing techniques for managing, processing, and analyzing graph databases, including graph pattern discovery [12,15,18,22], structurebased graph queries [5,6,10,11,19,23,27,26], etc. The substructure search problem, also called subgraph containment query, is that for a graph database and a given query graph, we want to find all data graphs which contain the query graph.…”

mentioning

confidence: 99%

Connected substructure similarity search

Shang

Lin

Zhang

et al. 2010

Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data

View full text Add to dashboard Cite

Substructure similarity search is to retrieve graphs that approximately contain a given query graph. It has many applications, e.g., detecting similar functions among chemical compounds. The problem is challenging as even testing subgraph containment between two graphs is NP-complete. Hence, existing techniques adopt the filtering-and-verification framework with the focus on developing effective and efficient techniques to remove non-promising graphs.Nevertheless, existing filtering techniques may be still unable to effectively remove many "low" quality candidates.To resolve this, in this paper we propose a novel indexing technique, GrafD-Index, to index graphs according to their "distances" to features. We characterize a tight condition under which the distance-based triangular inequality holds. We then develop lower and upper bounding techniques that exploit the GrafD-Index to (1) prune non-promising graphs and (2) include graphs whose similarities are guaranteed to exceed the given similarity threshold. Considering that the verification phase is not well studied and plays the dominant role in the whole process, we devise efficient algorithms to verify candidates. A comprehensive experiment using real datasets demonstrates that our proposed methods significantly outperform existing methods.

show abstract

mentioning

confidence: 99%

Connected substructure similarity search

Shang

Lin

Zhang

et al. 2010

Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data

View full text Add to dashboard Cite

show abstract

“…In recent years, a number of efficient and scalable algorithms have been developed to find patterns in the graphtransaction setting [7,44,22,20,45,18,21,30]. These algorithms are complete in the sense that they are guaranteed to discover all frequent subgraphs and were shown to scale to very large graph datasets.…”

Section: Introductionmentioning

confidence: 99%

Finding Frequent Patterns in a Large Sparse Graph

Kuramochi

Karypis

2004

Proceedings of the 2004 SIAM International Conference on Data Mining

134

180

View full text Add to dashboard Cite

This paper presents two algorithms based on the horizontal and vertical pattern discovery paradigms that find the connected subgraphs that have a sufficient number of edge-disjoint embeddings in a single large undirected labeled sparse graph. These algorithms use three different methods to determine the number of the edge-disjoint embeddings of a subgraph that are based on approximate and exact maximum independent set computations and use it to prune infrequent subgraphs. Experimental evaluation on real datasets from various domains show that both algorithms achieve good performance, scale well to sparse input graphs with more than 100,000 vertices, and significantly outperform a previously developed algorithm.

show abstract

“…Today, there are several algorithms proposed to solve graph mining problems. On chemical dataset, the algorithms are based on depth first visiting method to mining frequent substructures to achieve high performance [3][4][5] . But, in traffic datasets, it is very different from chemical datasets, where the size of graphs is much bigger than chemical datasets.…”

Section: Introductionmentioning

confidence: 99%

Two-Stage Data Mining Based Vehicle Navigation Algorithm in Urban Traffic Network

2012

AEF

View full text Add to dashboard Cite

Abstract. Along with the development of Intelligent Transportation System, traffic detectors collect numerous transportation state data in information databases and accumulate. Such data is greatly meaningful to the vehicle navigation. In this paper, we propose a noble two-stage algorithm about vehicle navigation by using data mining methods on the historical and current transportation dataset. This algorithm begins with picking sensitive data about start and end point in an urban traffic network, and data from related (or nearest) road fragments. Referring to current time and season, the algorithm gives an evaluation to every related road fragments and outputs a most reasonable route between start and end point. The experimental and theoretical analyzes show that this algorithm can form an efficient and effective route in reasonable time.

show abstract

Efficient mining of frequent subgraphs in the presence of isomorphism

Abstract: Abstract

Cited by 418 publications

References 8 publications

Connected substructure similarity search

Connected substructure similarity search

Finding Frequent Patterns in a Large Sparse Graph

Two-Stage Data Mining Based Vehicle Navigation Algorithm in Urban Traffic Network

Contact Info

Product

Resources

About