Statistically rigorous testing of clustering implementations
Document Type
Conference Proceeding
Publication Date
5-17-2019
Abstract
Clustering is a widely-used and well-studied AI branch, but defining clustering correctness, as well as verifying and validating clustering implementations, remains a challenge. To address this, we propose a statistically rigorous approach that couples differential clustering with statistical hypothesis testing, namely we conduct statistical hypothesis testing on the outcome (distribution) of differential clustering to reveal problematic outcomes. We employed this approach on widely-used clustering algorithms implemented in popular ML toolkits; the toolkits were tasked with clustering datasets from the Penn Machine Learning Benchmark. The results indicate that there are statistically significant differences in clustering outcomes in a variety of scenarios where users might not expect clustering outcome variation.
Identifier
85067125775 (Scopus)
ISBN
[9781728104928]
Publication Title
Proceedings 2019 IEEE International Conference on Artificial Intelligence Testing Aitest 2019
External Full Text Location
https://doi.org/10.1109/AITest.2019.000-1
First Page
91
Last Page
98
Grant
W911NF-13-2-0045
Fund Ref
National Science Foundation
Recommended Citation
Yin, Xin; Musco, Vincenzo; Neamtiu, Iulian; and Roshan, Usman, "Statistically rigorous testing of clustering implementations" (2019). Faculty Publications. 7590.
https://digitalcommons.njit.edu/fac_pubs/7590
