Combining
Multi-ratio Undersampling and
Metric Learning for Imbalanced Classification
(pp462-475)
Takahiro Komamizu
doi:
https://doi.org/10.26421/JDI2.4-5
Abstracts:
In classification, class
imbalance is a factor that degrades the classification performance
of many classification methods.
Resampling
is one widely accepted approach to the class imbalance; however, it
still suffers from an insufficient data space, which also degrades
performance. To overcome this, in this paper, an
undersampling-based imbalanced
classification framework,
MMEnsemble,
is proposed that incorporates metric learning into a
multi-ratio
undersampling-based ensemble.
This framework also overcomes a problem with determining the
appropriate sampling ratio in the
multi-ratio
ensemble method. It was evaluated by using 12 real-world
datasets.
It outperformed the state-of-the-art approaches of metric learning,
undersampling, and oversampling
in recall and
ROC-AUC,
and it performed comparably with them in terms of
Gmean
and F-measure metrics.
Key words:
imbalanced
classification,
undersampling,
ensemble, metric learning