Negative correlations in collaboration: Concepts and algorithms
- Publication Type:
- Conference Proceeding
- Citation:
- Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2010, pp. 463 - 471
- Issue Date:
- 2010-09-07
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
2013003010OK.pdf | Published version | 1.93 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
This paper studies efficient mining of negative correlations that pace in collaboration. A collaborating negative correlation is a negative correlation between two sets of variables rather than traditionally between a pair of variables. It signifies a synchronized value rise or fall of all variables within one set whenever all variables in the other set go jointly at the opposite trend. The time complexity is exponential in mining. The high efficiency of our algorithm is attributed to two factors: (i) the transformation of the original data into a bipartite graph database, and (ii) the mining of transpose closures from a wide transactional database. Applying to a Yeast gene expression data, we evaluate, by using Pearson's correlation coefficient and P-value, the biological relevance of collaborating negative correlations as an example among many real-life domains. © 2010 ACM.
Please use this identifier to cite or link to this item: