DNN-GDITD: Out-of-distribution detection via Deep Neural Network based Gaussian Descriptor for Imbalanced Tabular Data

TL;DR

This paper introduces DNN-GDITD, a novel out-of-distribution detection method for imbalanced tabular data that enhances classification accuracy and OOD detection using Gaussian descriptors and spherical decision boundaries.

Contribution

The paper proposes a new OOD detection algorithm for tabular data that can be integrated with any DNN, utilizing Gaussian descriptors and specialized loss functions for improved performance.

Findings

DNN-GDITD outperforms existing OOD detection algorithms on various tabular datasets.

The method effectively handles class imbalance and evolving data distributions.

Experimental results show high accuracy in OOD detection and classification tasks.

Abstract

Classification tasks present challenges due to class imbalances and evolving data distributions. Addressing these issues requires a robust method to handle imbalances while effectively detecting out-of-distribution (OOD) samples not encountered during training. This study introduces a novel OOD detection algorithm designed for tabular datasets, titled Deep Neural Network-based Gaussian Descriptor for Imbalanced Tabular Data (DNN-GDITD). The DNN-GDITD algorithm can be placed on top of any DNN to facilitate better classification of imbalanced data and OOD detection using spherical decision boundaries. Using a combination of Push, Score-based, and focal losses, DNN-GDITD assigns confidence scores to test data points, categorizing them as known classes or as an OOD sample. Extensive experimentation on tabular datasets demonstrates the effectiveness of DNN-GDITD compared to three OOD algorithms. Evaluation encompasses imbalanced and balanced scenarios on diverse tabular datasets, including a synthetic financial dispute dataset and publicly available tabular datasets like Gas Sensor, Drive Diagnosis, and MNIST, showcasing DNN-GDITD's versatility.