TSInterpret: A unified framework for time series interpretability

• URL: http://arxiv.org/abs/2208.05280v1
• Date: Wed, 10 Aug 2022 11:25:58 GMT
• Title: TSInterpret: A unified framework for time series interpretability
• Authors: Jacqueline H\"ollig, Cedric Kulbach, Steffen Thoma
• Abstract summary: Interpretability approaches and visualizations are diverse in use without a unified API or framework. We introduce TSInterpret, an easily open-source Python library for interpreting predictions of time series classifiers. The library features (i) state-of-the-art interpretability algorithms, (ii) exposes a unified API enabling users to work with explanations consistently and provides (iii) suitable for each explanation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the increasing application of deep learning algorithms to time series classification, especially in high-stake scenarios, the relevance of interpreting those algorithms becomes key. Although research in time series interpretability has grown, accessibility for practitioners is still an obstacle. Interpretability approaches and their visualizations are diverse in use without a unified API or framework. To close this gap, we introduce TSInterpret an easily extensible open-source Python library for interpreting predictions of time series classifiers that combines existing interpretation approaches into one unified framework. The library features (i) state-of-the-art interpretability algorithms, (ii) exposes a unified API enabling users to work with explanations consistently and provides (iii) suitable visualizations for each explanation.

Related papers

• Interactive Counterfactual Generation for Univariate Time Series [7.331969743532515]
  Our approach aims to enhance the transparency and understanding of deep learning models' decision processes. By abstracting user interactions with the projected data points, our method facilitates an intuitive generation of counterfactual explanations. We validate this method using the ECG5000 benchmark dataset, demonstrating significant improvements in interpretability and user understanding of time series classification.
  arXiv  Detail & Related papers  (2024-08-20T08:19:55Z)
• Global Knowledge Calibration for Fast Open-Vocabulary Segmentation [124.74256749281625]
  We introduce a text diversification strategy that generates a set of synonyms for each training category. We also employ a text-guided knowledge distillation method to preserve the generalizable knowledge of CLIP. Our proposed model achieves robust generalization performance across various datasets.
  arXiv  Detail & Related papers  (2023-03-16T09:51:41Z)
• Mimic: An adaptive algorithm for multivariate time series classification [11.49627617337276]
  Time series data are valuable but are often inscrutable. Gaining trust in time series classifiers for finance, healthcare, and other critical applications may rely on creating interpretable models. We propose a novel Mimic algorithm that retains the predictive accuracy of the strongest classifiers while introducing interpretability.
  arXiv  Detail & Related papers  (2021-11-08T04:47:31Z)
• Temporal Dependencies in Feature Importance for Time Series Predictions [4.082348823209183]
  We propose WinIT, a framework for evaluating feature importance in time series prediction settings. We demonstrate how the solution improves the appropriate attribution of features within time steps. WinIT achieves 2.47x better performance than FIT and other feature importance methods on real-world clinical MIMIC-mortality task.
  arXiv  Detail & Related papers  (2021-07-29T20:31:03Z)
• Interpretable Time-series Representation Learning With Multi-Level Disentanglement [56.38489708031278]
  Disentangle Time Series (DTS) is a novel disentanglement enhancement framework for sequential data. DTS generates hierarchical semantic concepts as the interpretable and disentangled representation of time-series. DTS achieves superior performance in downstream applications, with high interpretability of semantic concepts.
  arXiv  Detail & Related papers  (2021-05-17T22:02:24Z)
• Joint Contrastive Learning with Infinite Possibilities [114.45811348666898]
  This paper explores useful modifications of the recent development in contrastive learning via novel probabilistic modeling. We derive a particular form of contrastive loss named Joint Contrastive Learning (JCL)
  arXiv  Detail & Related papers  (2020-09-30T16:24:21Z)
• Captum: A unified and generic model interpretability library for PyTorch [49.72749684393332]
  We introduce a novel, unified, open-source model interpretability library for PyTorch. The library contains generic implementations of a number of gradient and perturbation-based attribution algorithms. It can be used for both classification and non-classification models.
  arXiv  Detail & Related papers  (2020-09-16T18:57:57Z)
• The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models [17.423179212411263]
  Language Interpretability Tool (LIT) is an open-source platform for visualization and understanding of NLP models. LIT integrates local explanations, aggregate analysis, and counterfactual generation into a streamlined, browser-based interface.
  arXiv  Detail & Related papers  (2020-08-12T06:07:44Z)
• Learning Interpretable and Discrete Representations with Adversarial Training for Unsupervised Text Classification [87.28408260725138]
  TIGAN learns to encode texts into two disentangled representations, including a discrete code and a continuous noise. The extracted topical words for representing latent topics show that TIGAN learns coherent and highly interpretable topics.
  arXiv  Detail & Related papers  (2020-04-28T02:53:59Z)
• TSInsight: A local-global attribution framework for interpretability in time-series data [5.174367472975529]
  We propose an auto-encoder to the classifier with a sparsity-inducing norm on its output and fine-tune it based on the gradients from the classifier and a reconstruction penalty. TSInsight learns to preserve features that are important for prediction by the classifier and suppresses those that are irrelevant. In contrast to most other attribution frameworks, TSInsight is capable of generating both instance-based and model-based explanations.
  arXiv  Detail & Related papers  (2020-04-06T19:34:25Z)
• Torch-Struct: Deep Structured Prediction Library [138.5262350501951]
  We introduce Torch-Struct, a library for structured prediction. Torch-Struct includes a broad collection of probabilistic structures accessed through a simple and flexible distribution-based API.
  arXiv  Detail & Related papers  (2020-02-03T16:43:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.