Expectation Propagation in GenSpace Graphs for Summarization

Download
  1. (PDF, 282 KB)
AuthorSearch for: ; Search for: ; Search for:
TypeArticle
ConferenceThe 9th International Conference on Data Warehousing and Knowledge Discovery (DaWak 2007), September 3-7, 2007., Regensburg, Germany
AbstractSummary mining aims to find interesting summaries for a data set and to use data mining techniques to improve the functionality of Online Analytical Processing (OLAP) systems. In this paper, we propose an interactive summary mining approach, called GenSpace summary mining, to find the interesting summaries based on user expectations. In the mining process, to record the user's evolving knowledge, the system needs to update and propagate new expectations. In this paper, we propose a linear method for consistently and efficiently propagating user expectations in a GenSpace graph. For a GenSpace graph where uninteresting nodes can be marked by the user before the mining process, we propose a greedy algorithm to determine the propagation paths in a GenSpace subgraph that reduces the time cost subject to a fixed amount of space.
Publication date
LanguageEnglish
AffiliationNRC Institute for Information Technology; National Research Council Canada
Peer reviewedNo
NRC number49355
NPARC number5765094
Export citationExport as RIS
Report a correctionReport a correction
Record identifierbb62158f-31f2-4eda-9389-61f7c572a050
Record created2009-03-29
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)