LoCoMotif: Discovering time-warped motifs in time series

• URL: http://arxiv.org/abs/2311.17582v1
• Date: Wed, 29 Nov 2023 12:18:46 GMT
• Title: LoCoMotif: Discovering time-warped motifs in time series
• Authors: Daan Van Wesenbeeck, Aras Yurtman, Wannes Meert, Hendrik Blockeel
• Abstract summary: Time Series Motif Discovery (TSMD) refers to the task of identifying patterns that occur multiple times in a time series. Existing methods for TSMD have one or more of the following limitations. We present a new method, LoCoMotif, that has none of these limitations.
• Score: 7.265353600305124
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Time Series Motif Discovery (TSMD) refers to the task of identifying patterns that occur multiple times (possibly with minor variations) in a time series. All existing methods for TSMD have one or more of the following limitations: they only look for the two most similar occurrences of a pattern; they only look for patterns of a pre-specified, fixed length; they cannot handle variability along the time axis; and they only handle univariate time series. In this paper, we present a new method, LoCoMotif, that has none of these limitations. The method is motivated by a concrete use case from physiotherapy. We demonstrate the value of the proposed method on this use case. We also introduce a new quantitative evaluation metric for motif discovery, and benchmark data for comparing TSMD methods. LoCoMotif substantially outperforms the existing methods, on top of being more broadly applicable.

Related papers

• Quantitative Evaluation of Motif Sets in Time Series [6.65064657162217]
  This paper introduces PROM and TSMD-Bench, a benchmark for quantitative evaluation of time series motif discovery methods. ProM provides a more comprehensive evaluation than existing metrics, and TSMD-Bench is a more challenging benchmark than earlier ones. The proposed approach enables large-scale, systematic performance comparisons in this field.
  arXiv  Detail & Related papers  (2024-12-12T15:13:34Z)
• Multiscale Dubuc: A New Similarity Measure for Time Series [1.024113475677323]
  We introduce the Multiscale Dubuc Distance measure and prove that it is a metric. We use 95 datasets from the UCR Time Series Classification Archive to compare MDD's performance with EuD, LCSS, and DTW. Our experiments show that MDD's overall success, without any case-specific customization, is comparable to DTW with optimized window sizes per dataset.
  arXiv  Detail & Related papers  (2024-11-15T18:38:18Z)
• Truncated Consistency Models [57.50243901368328]
  Training consistency models requires learning to map all intermediate points along PF ODE trajectories to their corresponding endpoints. We empirically find that this training paradigm limits the one-step generation performance of consistency models. We propose a new parameterization of the consistency function and a two-stage training procedure that prevents the truncated-time training from collapsing to a trivial solution.
  arXiv  Detail & Related papers  (2024-10-18T22:38:08Z)
• Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts [103.725112190618]
  This paper introduces Moirai-MoE, using a single input/output projection layer while delegating the modeling of diverse time series patterns to the sparse mixture of experts. Extensive experiments on 39 datasets demonstrate the superiority of Moirai-MoE over existing foundation models in both in-distribution and zero-shot scenarios.
  arXiv  Detail & Related papers  (2024-10-14T13:01:11Z)
• Which Tokens to Use? Investigating Token Reduction in Vision Transformers [64.99704164972513]
  We study the reduction patterns of 10 different token reduction methods using four image classification datasets. We find that the Top-K pruning method is a surprisingly strong baseline. The similarity of reduction patterns is a moderate-to-strong proxy for model performance.
  arXiv  Detail & Related papers  (2023-08-09T01:51:07Z)
• Matrix Profile XXVII: A Novel Distance Measure for Comparing Long Time Series [18.205595410817327]
  We introduce PRCIS, which stands for Pattern Representation Comparison in Series. PRCIS is a distance measure for long time series, which exploits recent progress in our ability to summarize time series with dictionaries.
  arXiv  Detail & Related papers  (2022-12-09T23:02:23Z)
• Motiflets -- Simple and Accurate Detection of Motifs in Time Series [3.6463708995502273]
  A time series motif intuitively is a short time series that repeats itself approximately the same within a larger time series. Motif discovery (MD) is the task of finding such motifs in a given input series. We present exact and approximate algorithms for finding k-Motiflets and analyze their complexity.
  arXiv  Detail & Related papers  (2022-06-08T08:22:28Z)
• Instance-wise Graph-based Framework for Multivariate Time Series Forecasting [69.38716332931986]
  We propose a simple yet efficient instance-wise graph-based framework to utilize the inter-dependencies of different variables at different time stamps. The key idea of our framework is aggregating information from the historical time series of different variables to the current time series that we need to forecast.
  arXiv  Detail & Related papers  (2021-09-14T07:38:35Z)
• An Investigation of Replay-based Approaches for Continual Learning [79.0660895390689]
  Continual learning (CL) is a major challenge of machine learning (ML) and describes the ability to learn several tasks sequentially without catastrophic forgetting (CF) Several solution classes have been proposed, of which so-called replay-based approaches seem very promising due to their simplicity and robustness. We empirically investigate replay-based approaches of continual learning and assess their potential for applications.
  arXiv  Detail & Related papers  (2021-08-15T15:05:02Z)
• The Semantic Adjacency Criterion in Time Intervals Mining [70.13948372218849]
  We propose a new pruning constraint during a frequent temporal-pattern discovery process, the Semantic Adjacency Criterion [SAC] We have defined three SAC versions, and tested their effect in three medical domains.
  arXiv  Detail & Related papers  (2021-01-11T12:23:49Z)
• Matrix Profile XXII: Exact Discovery of Time Series Motifs under DTW [1.282368486390644]
  We present the first scalable exact method to discover time series motifs under Dynamic Time Warping. Our algorithm can admissibly prune up to 99.99% of the DTW computations.
  arXiv  Detail & Related papers  (2020-09-16T19:35:43Z)
• MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation [12.386304516106854]
  Self-attention based models have achieved state-of-the-art performance in sequential recommendation task. These models rely on a simple positional embedding to exploit the sequential nature of the user's history. We propose MEANTIME which employs multiple types of temporal embeddings designed to capture various patterns from the user's behavior sequence.
  arXiv  Detail & Related papers  (2020-08-19T05:32:14Z)
• Evaluating the Disentanglement of Deep Generative Models through Manifold Topology [66.06153115971732]
  We present a method for quantifying disentanglement that only uses the generative model. We empirically evaluate several state-of-the-art models across multiple datasets.
  arXiv  Detail & Related papers  (2020-06-05T20:54:11Z)

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.