# ECATS: Explainable-by-design concept-based anomaly detection for time series

arXiv: https://arxiv.org/abs/2405.10608 · HTML: https://mlsanity.com/paper/2405.10608/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 17 May 2024.

## Builds on (most cited first, 18 of 18)

- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [On Completeness-aware Concept-Based Explanations in Deep Neural Networks](https://mlsanity.com/paper/1910.07969/) (2019)
- [LSTM Fully Convolutional Networks for Time Series Classification](https://mlsanity.com/paper/1709.05206/) (2017)
- [Deep Learning for Time Series Anomaly Detection: A Survey](https://mlsanity.com/paper/2211.05244/) (2022)
- [Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey](https://mlsanity.com/paper/1911.12116/) (2019)
- [Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey](https://mlsanity.com/paper/2104.00950/) (2021)
- [Interpretable Neural-Symbolic Concept Reasoning](https://mlsanity.com/paper/2304.14068/) (2023)
- [Now You See Me (CME): Concept-based Model Extraction](https://mlsanity.com/paper/2010.13233/) (2020)
- [Learning Bottleneck Concepts in Image Classification](https://mlsanity.com/paper/2304.10131/) (2023)
- [ConvTimeNet: A Pre-trained Deep Convolutional Neural Network for Time Series Classification](https://mlsanity.com/paper/1904.12546/) (2019)
- [Interpretable Classification of Time-Series Data using Efficient Enumerative Techniques](https://mlsanity.com/paper/1907.10265/) (2019)
- [Detecting and interpreting myocardial infarction using fully convolutional neural networks](https://mlsanity.com/paper/1806.07385/) (2018)
- [Focusing on What is Relevant: Time-Series Learning and Understanding using Attention](https://mlsanity.com/paper/1806.08523/) (2018)
- [Learning Model Checking and the Kernel Trick for Signal Temporal Logic on Stochastic Processes](https://mlsanity.com/paper/2201.09928/) (2022)
- [Societal, Economic, Ethical and Legal Challenges of the Digital Revolution: From Big Data to Deep Learning, Artificial Intelligence, and Manipulative Technologies](https://mlsanity.com/paper/1504.03751/) (2015)

## Built on by (most cited first, 1 of 1)

- [Interpretability for Time Series Transformers using A Concept Bottleneck Framework](https://mlsanity.com/paper/2410.06070/) (2024)

## Abstract (arXiv)

Deep learning methods for time series have already reached excellent performances in both prediction and classification tasks, including anomaly detection. However, the complexity inherent in Cyber Physical Systems (CPS) creates a challenge when it comes to explainability methods. To overcome this inherent lack of interpretability, we propose ECATS, a concept-based neuro-symbolic architecture where concepts are represented as Signal Temporal Logic (STL) formulae. Leveraging kernel-based methods for STL, concept embeddings are learnt in an unsupervised manner through a cross-attention mechanism. The network makes class predictions through these concept embeddings, allowing for a meaningful explanation to be naturally extracted for each input. Our preliminary experiments with a simple CPS-based dataset show that our model is able to achieve great classification performance while ensuring local interpretability.