AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dominici, Gabriele, Barbiero, Pietro, Giannini, Francesco, Gjoreski, Martin, Langhenirich, Marc
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910460093136896
author Dominici, Gabriele
Barbiero, Pietro
Giannini, Francesco
Gjoreski, Martin
Langhenirich, Marc
author_facet Dominici, Gabriele
Barbiero, Pietro
Giannini, Francesco
Gjoreski, Martin
Langhenirich, Marc
contents Interpretable deep learning aims at developing neural architectures whose decision-making processes could be understood by their users. Among these techniqes, Concept Bottleneck Models enhance the interpretability of neural networks by integrating a layer of human-understandable concepts. These models, however, necessitate training a new model from the beginning, consuming significant resources and failing to utilize already trained large models. To address this issue, we introduce "AnyCBM", a method that transforms any existing trained model into a Concept Bottleneck Model with minimal impact on computational resources. We provide both theoretical and experimental insights showing the effectiveness of AnyCBMs in terms of classification performances and effectivenss of concept-based interventions on downstream tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16508
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Model
Dominici, Gabriele
Barbiero, Pietro
Giannini, Francesco
Gjoreski, Martin
Langhenirich, Marc
Machine Learning
Interpretable deep learning aims at developing neural architectures whose decision-making processes could be understood by their users. Among these techniqes, Concept Bottleneck Models enhance the interpretability of neural networks by integrating a layer of human-understandable concepts. These models, however, necessitate training a new model from the beginning, consuming significant resources and failing to utilize already trained large models. To address this issue, we introduce "AnyCBM", a method that transforms any existing trained model into a Concept Bottleneck Model with minimal impact on computational resources. We provide both theoretical and experimental insights showing the effectiveness of AnyCBMs in terms of classification performances and effectivenss of concept-based interventions on downstream tasks.
title AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Model
topic Machine Learning
url https://arxiv.org/abs/2405.16508