Explaining Deep Learning Hidden Neuron Activations using Concept Induction

TL;DR

This paper introduces a method that uses large-scale background knowledge and symbolic reasoning to automatically interpret hidden neuron activations in deep learning models, enhancing explainability.

Contribution

It presents a novel automated approach combining concept induction and background knowledge to interpret hidden neurons in neural networks.

Findings

Automatically attaches meaningful labels to neurons

Uses Wikipedia concept hierarchy for interpretation

Demonstrates effectiveness in CNN hidden layers

Abstract

One of the current key challenges in Explainable AI is in correctly interpreting activations of hidden neurons. It seems evident that accurate interpretations thereof would provide insights into the question what a deep learning system has internally \emph{detected} as relevant on the input, thus lifting some of the black box character of deep learning systems. The state of the art on this front indicates that hidden node activations appear to be interpretable in a way that makes sense to humans, at least in some cases. Yet, systematic automated methods that would be able to first hypothesize an interpretation of hidden neuron activations, and then verify it, are mostly missing. In this paper, we provide such a method and demonstrate that it provides meaningful interpretations. It is based on using large-scale background knowledge -- a class hierarchy of approx. 2 million classes curated from the Wikipedia Concept Hierarchy -- together with a symbolic reasoning approach called \emph{concept induction} based on description logics that was originally developed for applications in the Semantic Web field. Our results show that we can automatically attach meaningful labels from the background knowledge to individual neurons in the dense layer of a Convolutional Neural Network through a hypothesis and verification process.