VC-dimension and Rademacher Averages of Subgraphs, with Applications to Graph Mining | IEEE Conference Publication | IEEE Xplore
Scheduled Maintenance: On Tuesday, 25 February, IEEE Xplore will undergo scheduled maintenance from 1:00-5:00 PM ET (1800-2200 UTC). During this time, there may be intermittent impact on performance. We apologize for any inconvenience.

VC-dimension and Rademacher Averages of Subgraphs, with Applications to Graph Mining


Abstract:

Frequent subgraph mining is a fundamental task in the analysis of collections of graphs. While several exact approaches have been proposed, it remains computationally cha...Show More

Abstract:

Frequent subgraph mining is a fundamental task in the analysis of collections of graphs. While several exact approaches have been proposed, it remains computationally challenging on large graph datasets due to its inherent link to the subgraph isomorphism problem and the huge number of candidate patterns even for fairly small subgraphs.In this work, we study two statistical learning measures of complexity, VC-dimension and Rademacher averages, for subgraphs, and derive efficiently computable bounds for both. We show how such bounds can be applied to devise efficient sampling-based approaches for rigorously approximating the solution of the frequent subgraph mining problem. We also show that our bounds can be used for true frequent subgraph mining, which requires to identify subgraphs generated with probability above a given threshold from an unknown generative process using samples from such process. Our extensive experimental evaluation on real datasets shows that our bounds lead to efficiently computable, high-quality approximations for both applications.
Date of Conference: 03-07 April 2023
Date Added to IEEE Xplore: 26 July 2023
ISBN Information:

ISSN Information:

Conference Location: Anaheim, CA, USA

Funding Agency:


References

References is not available for this document.