# Learning to Explain with Complemental Examples

## TL;DR

This paper introduces a novel framework for generating multimodal explanations combining linguistic and visual examples, maximizing their complementarity through interaction information to improve interpretability.

## Contribution

It proposes a new neural network-based method that jointly generates and optimizes complementary linguistic and visual explanations for classification decisions.

## Key findings

- Effective in producing complementary explanations
- Improves interpretability of classification models
- Validated on multiple datasets

## Abstract

This paper addresses the generation of explanations with visual examples. Given an input sample, we build a system that not only classifies it to a specific category, but also outputs linguistic explanations and a set of visual examples that render the decision interpretable. Focusing especially on the complementarity of the multimodal information, i.e., linguistic and visual examples, we attempt to achieve it by maximizing the interaction information, which provides a natural definition of complementarity from an information theoretical viewpoint. We propose a novel framework to generate complemental explanations, on which the joint distribution of the variables to explain, and those to be explained is parameterized by three different neural networks: predictor, linguistic explainer, and example selector. Explanation models are trained collaboratively to maximize the interaction information to ensure the generated explanation are complemental to each other for the target. The results of experiments conducted on several datasets demonstrate the effectiveness of the proposed method.