# MARGIN: Uncovering Deep Neural Networks using Graph Signal Analysis

arXiv: https://arxiv.org/abs/1711.05407 · HTML: https://mlsanity.com/paper/1711.05407/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2017.

## Built on by (most cited first, 2 of 2)

- [Explaining Latent Representations with a Corpus of Examples](https://mlsanity.com/paper/2110.15355/) (2021)
- [Graphs as Tools to Improve Deep Learning Methods](https://mlsanity.com/paper/2110.03999/) (2021)

## Abstract (arXiv)

Interpretability has emerged as a crucial aspect of building trust in machine learning systems, aimed at providing insights into the working of complex neural networks that are otherwise opaque to a user. There are a plethora of existing solutions addressing various aspects of interpretability ranging from identifying prototypical samples in a dataset to explaining image predictions or explaining mis-classifications. While all of these diverse techniques address seemingly different aspects of interpretability, we hypothesize that a large family of interepretability tasks are variants of the same central problem which is identifying relative change in a model's prediction. This paper introduces MARGIN, a simple yet general approach to address a large set of interpretability tasks MARGIN exploits ideas rooted in graph signal analysis to determine influential nodes in a graph, which are defined as those nodes that maximally describe a function defined on the graph. By carefully defining task-specific graphs and functions, we demonstrate that MARGIN outperforms existing approaches in a number of disparate interpretability challenges.