Abstract | ||
---|---|---|
We address the problem of outlying aspects mining: given a query object and a reference multidimensional data set, how can we discover what aspects (i.e., subsets of features or subspaces) make the query object most outlying? Outlying aspects mining can be used to explain any data point of interest, which itself might be an inlier or outlier. In this paper, we investigate several open challenges faced by existing outlying aspects mining techniques and propose novel solutions, including (a) how to design effective scoring functions that are unbiased with respect to dimensionality and yet being computationally efficient, and (b) how to efficiently search through the exponentially large search space of all possible subspaces. We formalize the concept of dimensionality unbiasedness, a desirable property of outlyingness measures. We then characterize existing scoring measures as well as our novel proposed ones in terms of efficiency, dimensionality unbiasedness and interpretability. Finally, we evaluate the effectiveness of different methods for outlying aspects discovery and demonstrate the utility of our proposed approach on both large real and synthetic data sets. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/s10618-016-0453-2 | Data Min. Knowl. Discov. |
Keywords | Field | DocType |
Outlying aspects mining,Subspace selection,Outlier explanation | Data mining,Interpretability,Computer science,Outlier,Curse of dimensionality,Linear subspace,Artificial intelligence,Point of interest,Synthetic data sets,Machine learning | Journal |
Volume | Issue | ISSN |
30 | 6 | 1384-5810 |
Citations | PageRank | References |
14 | 0.62 | 19 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xuan Vinh Nguyen | 1 | 749 | 42.94 |
Jeffrey Chan | 2 | 427 | 36.55 |
Simone Romano | 3 | 79 | 5.66 |
James Bailey | 4 | 2172 | 164.56 |
Christopher Leckie | 5 | 2422 | 155.20 |
kotagiri ramamohanarao | 6 | 4716 | 993.87 |
Jian Pei | 7 | 19002 | 995.54 |