CENDRe：基于自然域表示的 CNN 概念提取方法
CENDRe: Concept Extraction with Natural Domain Representations
AI 导读
arXiv 论文提出面向 CNN 时间序列分类的概念提取方法 CENDRe，通过两阶段聚类与 silhouette 引导聚合自动确定概念数量，并用 presence score 梯度生成定位掩码，经可逆映射（如 Fourier transform）实现不同信号域的定位。
正文 · 原文
Abstract:Convolutional neural networks (CNNs) are widely used for time-series classification, but their deployment in critical contexts requires understanding the patterns across signal domains that drive their predictions (e.g., temporal or spectral). Concept extraction (CE) methods identify such patterns by analyzing representations within the models' latent space. However, existing time-series CE methods have three limitations: they operate only in the time domain and cannot locate features in other domains, they depend on a predefined number of concepts that biases them, and they produce localizations misaligned with the regions the model uses. We address these limitations with CENDRe, a concept extraction method for CNNs. For concept discovery, we propose a procedure that clusters per-timestep latent representations in two stages, with a silhouette-guided aggregation that selects the number of concepts automatically. For localization, we define a presence score that contrasts the latent representations with their prototypes, and use its gradients to produce masks that concentrate on the regions driving the concept. These gradients, propagated through a differentiable invertible mapping of the input such as a Fourier transform, yield localizations for the same concepts in different domains. Finally, each concept receives a relevance score that quantifies its contribution to each class. On synthetic benchmarks, CENDRe achieves representation correctness comparable to state-of-the-art CE methods and higher importance correctness, while producing visualizations in different domains. On real bearing-fault data, CENDRe extracts the frequency bands driving the model's predictions, located in regions commonly inspected for fault diagnosis, producing evidence to assess the model that time-domain CE methods cannot.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.29621 [cs.LG] |
| (or arXiv:2607.29621v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2607.29621 arXiv-issued DOI via DataCite |
Submission history
From: Antonia Holzapfel [view email]
[v1]
Fri, 31 Jul 2026 16:56:27 UTC (17,026 KB)
[v2]
Wed, 11 Nov 2026 17:20:54 UTC (17,026 KB)
来源：arXiv cs.AI · arxiv.org