CF-OPT: Counterfactual Explanations for Structured Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vivier-Ardisson, Germain, Forel, Alexandre, Parmentier, Axel, Vidal, Thibaut
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914820486332416
author Vivier-Ardisson, Germain
Forel, Alexandre
Parmentier, Axel
Vidal, Thibaut
author_facet Vivier-Ardisson, Germain
Forel, Alexandre
Parmentier, Axel
Vidal, Thibaut
contents Optimization layers in deep neural networks have enjoyed a growing popularity in structured learning, improving the state of the art on a variety of applications. Yet, these pipelines lack interpretability since they are made of two opaque layers: a highly non-linear prediction model, such as a deep neural network, and an optimization layer, which is typically a complex black-box solver. Our goal is to improve the transparency of such methods by providing counterfactual explanations. We build upon variational autoencoders a principled way of obtaining counterfactuals: working in the latent space leads to a natural notion of plausibility of explanations. We finally introduce a variant of the classic loss for VAE training that improves their performance in our specific structured context. These provide the foundations of CF-OPT, a first-order optimization algorithm that can find counterfactual explanations for a broad class of structured learning architectures. Our numerical results show that both close and plausible explanations can be obtained for problems from the recent literature.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18293
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CF-OPT: Counterfactual Explanations for Structured Prediction
Vivier-Ardisson, Germain
Forel, Alexandre
Parmentier, Axel
Vidal, Thibaut
Machine Learning
Optimization layers in deep neural networks have enjoyed a growing popularity in structured learning, improving the state of the art on a variety of applications. Yet, these pipelines lack interpretability since they are made of two opaque layers: a highly non-linear prediction model, such as a deep neural network, and an optimization layer, which is typically a complex black-box solver. Our goal is to improve the transparency of such methods by providing counterfactual explanations. We build upon variational autoencoders a principled way of obtaining counterfactuals: working in the latent space leads to a natural notion of plausibility of explanations. We finally introduce a variant of the classic loss for VAE training that improves their performance in our specific structured context. These provide the foundations of CF-OPT, a first-order optimization algorithm that can find counterfactual explanations for a broad class of structured learning architectures. Our numerical results show that both close and plausible explanations can be obtained for problems from the recent literature.
title CF-OPT: Counterfactual Explanations for Structured Prediction
topic Machine Learning
url https://arxiv.org/abs/2405.18293