{
  "id": "2009.04796",
  "version": "v2",
  "published": "2020-09-10T11:55:53.000Z",
  "updated": "2020-12-10T10:10:37.000Z",
  "title": "XCM: An Explainable Convolutional Neural Network for Multivariate Time Series Classification",
  "authors": [
    "Kevin Fauvel",
    "Tao Lin",
    "Véronique Masson",
    "Élisa Fromont",
    "Alexandre Termier"
  ],
  "comment": "arXiv admin note: text overlap with arXiv:2005.03645",
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "We present XCM, an eXplainable Convolutional neural network for Multivariate time series classification. XCM is a new compact convolutional neural network which extracts information relative to the observed variables and time directly from the input data. Thus, XCM architecture enables a good generalization ability on both small and large datasets, while allowing the full exploitation of a faithful post-hoc model-specific explainability method (Gradient-weighted Class Activation Mapping) by precisely identifying the observed variables and timestamps of the input data that are important for predictions. Our evaluation firstly shows that XCM outperforms the state-of-the-art multivariate time series classifiers on both the large and small public UEA datasets. Furthermore, following the illustration of the performance and explainability of XCM on a synthetic dataset, we present how XCM can outperform the current most accurate state-of-the-art algorithm on a real-world application while enhancing explainability by providing faithful and more informative explanations.",
  "revisions": [
    {
      "version": "v2",
      "updated": "2020-12-10T10:10:37.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "multivariate time series classification",
      "explainable convolutional neural network",
      "post-hoc model-specific explainability method",
      "multivariate time series classifiers"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}