.png){kind=icon}
.png){kind=icon}
Return
DISCONA: distributed sample compression for nearest neighbor algorithm
.png){kind=icon}
OA
AI
DOI：10.1007/s10489-023-04482-y.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Sample compression using epsilon-net effectively reduces the number of labeled instances required for accurate classification with nearest neighbor algorithms. However, one-shot construction of an epsilon-net can be extremely challenging in large-scale distributed data sets. We explore two approaches for distributed sample compression: one where local epsilon-net is constructed for each data partition and then merged during an aggregation phase, and one where a single backbone of an epsilon-net is constructed from one partition and aggregates target label distributions from other partitions. Both approaches are applied to the problem of malware detection in a complex, real-world data set of Android apps using the nearest neighbor algorithm. Examination of the compression rate, computational efficiency, and predictive power shows that a single backbone of an epsilon-net attains favorable performance while achieving a compression rate of 99%.
Keywords:
Distributed machine learning
Malware detection
Nearest neighbors
Sample compression
Big data
Journal
IF:
3.5
Papers:
7.5K
Citations:
1.7W