# Understanding Interpretability by generalized distillation in Supervised Classification

Source: [Understanding Interpretability by generalized distillation in Supervised Classification](<https://www.sota2.com/research/paper/68fa74ae1e209131cea6332a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:15:34.723Z

Authors: Adit Agarwal, K.K. Shukla, Arjan Kuijper, Anirban Mukhopadhyay

Published: 2020-12-05T17:42:50.000Z

## Abstract

The ability to interpret decisions taken by Machine Learning (ML) models is fundamental to encourage trust and reliability in different practical applications. Recent interpretation strategies focus on human understanding of the underlying decision mechanisms of the complex ML models. However, these strategies are restricted by the subjective biases of humans. To dissociate from such human biases, we propose an interpretation-by-distillation formulation that is defined relative to other ML models. We generalize the distillation technique for quantifying interpretability, using an information-theoretic perspective, removing the role of ground-truth from the definition of interpretability. Our work defines the entropy of supervised classification models, providing bounds on the entropy of Piece-Wise Linear Neural Networks (PWLNs), along with the first theoretical bounds on the interpretability of PWLNs. We evaluate our proposed framework on the MNIST, Fashion-MNIST and Stanford40 datasets and demonstrate the applicability of the proposed theoretical framework in different supervised classification scenarios.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2012.03089>)

[PDF](<https://arxiv.org/pdf/2012.03089.pdf>)
