Layer-wise Relevance Propagation for Explainable Recommendations

TL;DR

This paper introduces a method using layer-wise relevance propagation to generate pixel-level explanations for deep learning-based image recommendation models, enhancing interpretability of model decisions.

Contribution

It applies layer-wise relevance propagation to deep CNNs in recommendation systems, providing detailed visual explanations of model predictions.

Findings

Effective pixel-level explanations generated

Improved interpretability demonstrated on Amazon dataset

Method outperforms baseline explanation techniques

Abstract

In this paper, we tackle the problem of explanations in a deep-learning based model for recommendations by leveraging the technique of layer-wise relevance propagation. We use a Deep Convolutional Neural Network to extract relevant features from the input images before identifying similarity between the images in feature space. Relationships between the images are identified by the model and layer-wise relevance propagation is used to infer pixel-level details of the images that may have significantly informed the model's choice. We evaluate our method on an Amazon products dataset and demonstrate the efficacy of our approach.