Enhancing Interpretability Through Loss-Defined Classification Objective in Structured Latent Spaces

TL;DR

This paper presents Latent Boost, a novel method that enhances interpretability and training efficiency in supervised classification by integrating distance metric learning into latent space representations, promoting clearer class clustering.

Contribution

The paper introduces Latent Boost, a new approach that combines metric learning with classification to improve interpretability and training speed without significant additional costs.

Findings

Higher Silhouette scores indicating better class clustering

Faster convergence during training

Broad applicability across datasets

Abstract

Supervised machine learning often operates on the data-driven paradigm, wherein internal model parameters are autonomously optimized to converge predicted outputs with the ground truth, devoid of explicitly programming rules or a priori assumptions. Although data-driven methods have yielded notable successes across various benchmark datasets, they inherently treat models as opaque entities, thereby limiting their interpretability and yielding a lack of explanatory insights into their decision-making processes. In this work, we introduce Latent Boost, a novel approach that integrates advanced distance metric learning into supervised classification tasks, enhancing both interpretability and training efficiency. Thus during training, the model is not only optimized for classification metrics of the discrete data points but also adheres to the rule that the collective representation zones of each class should be sharply clustered. By leveraging the rich structural insights of intermediate model layer latent representations, Latent Boost improves classification interpretability, as demonstrated by higher Silhouette scores, while accelerating training convergence. These performance and latent structural benefits are achieved with minimum additional cost, making it broadly applicable across various datasets without requiring data-specific adjustments. Furthermore, Latent Boost introduces a new paradigm for aligning classification performance with improved model transparency to address the challenges of black-box models.