# Concept Extraction for Time Series with ECLAD-ts

arXiv: https://arxiv.org/abs/2504.05024 · HTML: https://mlsanity.com/paper/2504.05024/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [FinBERT: Financial Sentiment Analysis with Pre-trained Language Models](https://mlsanity.com/paper/1908.10063/) (2019)
- [Marian: Fast Neural Machine Translation in C++](https://mlsanity.com/paper/1804.00344/) (2018)
- [QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension](https://mlsanity.com/paper/1804.09541/) (2018)
- [TweetNLP: Cutting-Edge Natural Language Processing for Social Media](https://mlsanity.com/paper/2206.14774/) (2022)
- [Pre-trained Language Models for the Legal Domain: A Case Study on Indian Law](https://mlsanity.com/paper/2209.06049/) (2022)
- [Clinical Text Classification with Rule-based Features and Knowledge-guided Convolutional Neural Networks](https://mlsanity.com/paper/1807.07425/) (2018)
- [Bidirectional Recurrent Neural Networks for Medical Event Detection in Electronic Health Records](https://mlsanity.com/paper/1606.07953/) (2016)
- [Low Resource Text Classification with ULMFit and Backtranslation](https://mlsanity.com/paper/1903.09244/) (2019)
- [Data Expansion using Back Translation and Paraphrasing for Hate Speech Detection](https://mlsanity.com/paper/2106.04681/) (2021)
- [Data Augmentation with Paraphrase Generation and Entity Extraction for Multimodal Dialogue System](https://mlsanity.com/paper/2205.04006/) (2022)
- [ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization](https://mlsanity.com/paper/2201.05313/) (2022)
- [Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks](https://mlsanity.com/paper/2210.10343/) (2022)

## Built on by (most cited first, 2 of 2)

- [xaitimesynth: A Python Package for Evaluating Attribution Methods for Time Series with Synthetic Ground Truth](https://mlsanity.com/paper/2603.06781/) (2026)
- [CENDRe: Concept Extraction with Natural Domain Representations](https://mlsanity.com/paper/2607.29621/) (2026)

## Abstract (arXiv)

Convolutional neural networks (CNNs) for time series classification (TSC) are being increasingly used in applications ranging from quality prediction to medical diagnosis. The black box nature of these models makes understanding their prediction process difficult. This issue is crucial because CNNs are prone to learning shortcuts and biases, compromising their robustness and alignment with human expectations. To assess whether such mechanisms are being used and the associated risk, it is essential to provide model explanations that reflect the inner workings of the model. Concept Extraction (CE) methods offer such explanations, but have mostly been developed for the image domain so far, leaving a gap in the time series domain. In this work, we present a CE and localization method tailored to the time series domain, based on the ideas of CE methods for images. We propose the novel method ECLAD-ts, which provides post-hoc global explanations based on how the models encode subsets of the input at different levels of abstraction. For this, concepts are produced by clustering timestep-wise aggregations of CNN activation maps, and their importance is computed based on their impact on the prediction process. We evaluate our method on synthetic and natural datasets. Furthermore, we assess the advantages and limitations of CE in time series through empirical results. Our results show that ECLAD-ts effectively explains models by leveraging their internal representations, providing useful insights about their prediction process.