# Influence-Directed Explanations for Deep Convolutional Networks

Source: [Influence-Directed Explanations for Deep Convolutional Networks](<https://www.sota2.com/research/paper/68fa65171e209131cea08363>)

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

Data updated: 2025-10-25T21:18:52.954Z

Authors: Klas Leino, Shayak Sen, Anupam Datta, Matt Fredrikson, Linyi Li

Published: 2018-02-11T18:28:56.000Z

## Abstract

We study the problem of explaining a rich class of behavioral properties of deep neural networks. Distinctively, our influence-directed explanations approach this problem by peering inside the network to identify neurons with high influence on a quantity and distribution of interest, using an axiomatically-justified influence measure, and then providing an interpretation for the concepts these neurons represent. We evaluate our approach by demonstrating a number of its unique capabilities on convolutional neural networks trained on ImageNet. Our evaluation demonstrates that influence-directed explanations (1) identify influential concepts that generalize across instances, (2) can be used to extract the "essence" of what the network learned about a class, and (3) isolate individual features the network uses to make decisions and distinguish related classes.

## 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/1802.03788>)

[PDF](<https://arxiv.org/pdf/1802.03788.pdf>)