ConceptFlow: Hierarchical and Fine-grained Concept-Based Explanation for Convolutional Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mu, Xinyu, Dou, Hui, Shen, Furao, Zhao, Jian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914051300261888
author Mu, Xinyu
Dou, Hui
Shen, Furao
Zhao, Jian
author_facet Mu, Xinyu
Dou, Hui
Shen, Furao
Zhao, Jian
contents Concept-based interpretability for Convolutional Neural Networks (CNNs) aims to align internal model representations with high-level semantic concepts, but existing approaches largely overlook the semantic roles of individual filters and the dynamic propagation of concepts across layers. To address these limitations, we propose ConceptFlow, a concept-based interpretability framework that simulates the internal "thinking path" of a model by tracing how concepts emerge and evolve across layers. ConceptFlow comprises two key components: (i) concept attentions, which associate each filter with relevant high-level concepts to enable localized semantic interpretation, and (ii) conceptual pathways, derived from a concept transition matrix that quantifies how concepts propagate and transform between filters. Together, these components offer a unified and structured view of internal model reasoning. Experimental results demonstrate that ConceptFlow yields semantically meaningful insights into model reasoning, validating the effectiveness of concept attentions and conceptual pathways in explaining decision behavior. By modeling hierarchical conceptual pathways, ConceptFlow provides deeper insight into the internal logic of CNNs and supports the generation of more faithful and human-aligned explanations.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18147
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ConceptFlow: Hierarchical and Fine-grained Concept-Based Explanation for Convolutional Neural Networks
Mu, Xinyu
Dou, Hui
Shen, Furao
Zhao, Jian
Machine Learning
Artificial Intelligence
Concept-based interpretability for Convolutional Neural Networks (CNNs) aims to align internal model representations with high-level semantic concepts, but existing approaches largely overlook the semantic roles of individual filters and the dynamic propagation of concepts across layers. To address these limitations, we propose ConceptFlow, a concept-based interpretability framework that simulates the internal "thinking path" of a model by tracing how concepts emerge and evolve across layers. ConceptFlow comprises two key components: (i) concept attentions, which associate each filter with relevant high-level concepts to enable localized semantic interpretation, and (ii) conceptual pathways, derived from a concept transition matrix that quantifies how concepts propagate and transform between filters. Together, these components offer a unified and structured view of internal model reasoning. Experimental results demonstrate that ConceptFlow yields semantically meaningful insights into model reasoning, validating the effectiveness of concept attentions and conceptual pathways in explaining decision behavior. By modeling hierarchical conceptual pathways, ConceptFlow provides deeper insight into the internal logic of CNNs and supports the generation of more faithful and human-aligned explanations.
title ConceptFlow: Hierarchical and Fine-grained Concept-Based Explanation for Convolutional Neural Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.18147