Dynamic Sparse Network for Time Series Classification: Learning What to "see''

• URL: http://arxiv.org/abs/2212.09840v1
• Date: Mon, 19 Dec 2022 20:32:27 GMT
• Title: Dynamic Sparse Network for Time Series Classification: Learning What to "see''
• Authors: Qiao Xiao, Boqian Wu, Yu Zhang, Shiwei Liu, Mykola Pechenizkiy, Elena Mocanu, Decebal Constantin Mocanu
• Abstract summary: We propose a dynamic sparse network (DSN) with sparse connections for time series classification (TSC) The kernels in each sparse layer are sparse and can be explored under the constraint regions by dynamic sparse training, which makes it possible to reduce the resource cost.
• Score: 17.705879794117912
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The receptive field (RF), which determines the region of time series to be ``seen'' and used, is critical to improve the performance for time series classification (TSC). However, the variation of signal scales across and within time series data, makes it challenging to decide on proper RF sizes for TSC. In this paper, we propose a dynamic sparse network (DSN) with sparse connections for TSC, which can learn to cover various RF without cumbersome hyper-parameters tuning. The kernels in each sparse layer are sparse and can be explored under the constraint regions by dynamic sparse training, which makes it possible to reduce the resource cost. The experimental results show that the proposed DSN model can achieve state-of-art performance on both univariate and multivariate TSC datasets with less than 50\% computational cost compared with recent baseline methods, opening the path towards more accurate resource-aware methods for time series analyses. Our code is publicly available at: https://github.com/QiaoXiao7282/DSN.

Related papers

• Concrete Dense Network for Long-Sequence Time Series Clustering [4.307648859471193]
  Time series clustering is fundamental in data analysis for discovering temporal patterns. Deep temporal clustering methods have been trying to integrate the canonical k-means into end-to-end training of neural networks. LoSTer is a novel dense autoencoder architecture for the long-sequence time series clustering problem.
  arXiv  Detail & Related papers  (2024-05-08T12:31:35Z)
• TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals [58.865901821451295]
  We present a novel two-stream feature fusion "Tensor-Convolution and Convolution-Transformer Network" (TCCT-Net) architecture. To better learn the meaningful patterns in the temporal-spatial domain, we design a "CT" stream that integrates a hybrid convolutional-transformer. In parallel, to efficiently extract rich patterns from the temporal-frequency domain, we introduce a "TC" stream that uses Continuous Wavelet Transform (CWT) to represent information in a 2D tensor form.
  arXiv  Detail & Related papers  (2024-04-15T06:01:48Z)
• Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data [50.84488941336865]
  We propose a novel method called Fully- Spatial-Temporal Graph Neural Network (FC-STGNN) For graph construction, we design a decay graph to connect sensors across all timestamps based on their temporal distances. For graph convolution, we devise FC graph convolution with a moving-pooling GNN layer to effectively capture the ST dependencies for learning effective representations.
  arXiv  Detail & Related papers  (2023-09-11T08:44:07Z)
• Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series [26.77596449192451]
  Irregularly sampled time series are ubiquitous in several application domains, leading to sparse, not fully-observed and non-aligned observations. Standard sequential neural networks (RNNs) and convolutional neural networks (CNNs) consider regular spacing between observation times, posing significant challenges to irregular time series modeling. We parameterize convolutional layers by employing time-explicitly irregular kernels.
  arXiv  Detail & Related papers  (2023-08-06T21:10:30Z)
• Enhancing Multivariate Time Series Classifiers through Self-Attention and Relative Positioning Infusion [4.18804572788063]
  Time Series Classification (TSC) is an important and challenging task for many visual computing applications. We propose two novel attention blocks that can enhance deep learning-based TSC approaches. We show that adding the proposed attention blocks improves base models' average accuracy by up to 3.6%.
  arXiv  Detail & Related papers  (2023-02-13T20:50:34Z)
• HyperTime: Implicit Neural Representation for Time Series [131.57172578210256]
  Implicit neural representations (INRs) have recently emerged as a powerful tool that provides an accurate and resolution-independent encoding of data. In this paper, we analyze the representation of time series using INRs, comparing different activation functions in terms of reconstruction accuracy and training convergence speed. We propose a hypernetwork architecture that leverages INRs to learn a compressed latent representation of an entire time series dataset.
  arXiv  Detail & Related papers  (2022-08-11T14:05:51Z)
• Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis [32.45387153404849]
  We propose a novel framework referred as RObust Training for Time-Series (RO-TS) to create robust DNNs for time-series classification tasks. We show the generality and advantages of our formulation using the summation structure over time-series alignments. Our experiments on real-world benchmarks demonstrate that RO-TS creates more robust DNNs when compared to adversarial training.
  arXiv  Detail & Related papers  (2022-07-09T17:21:03Z)
• Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [56.98668484450857]
  This paper explores a novel frequency-aware dynamic network for dividing the input into multiple parts according to its coefficients in the discrete cosine transform (DCT) domain. In practice, the high-frequency part will be processed using expensive operations and the lower-frequency part is assigned with cheap operations to relieve the computation burden. Experiments conducted on benchmark SISR models and datasets show that the frequency-aware dynamic network can be employed for various SISR neural architectures.
  arXiv  Detail & Related papers  (2021-03-15T12:54:26Z)
• Deep Cellular Recurrent Network for Efficient Analysis of Time-Series Data with Spatial Information [52.635997570873194]
  This work proposes a novel deep cellular recurrent neural network (DCRNN) architecture to process complex multi-dimensional time series data with spatial information. The proposed architecture achieves state-of-the-art performance while utilizing substantially less trainable parameters when compared to comparable methods in the literature.
  arXiv  Detail & Related papers  (2021-01-12T20:08:18Z)
• Deep Networks for Direction-of-Arrival Estimation in Low SNR [89.45026632977456]
  We introduce a Convolutional Neural Network (CNN) that is trained from mutli-channel data of the true array manifold matrix. We train a CNN in the low-SNR regime to predict DoAs across all SNRs. Our robust solution can be applied in several fields, ranging from wireless array sensors to acoustic microphones or sonars.
  arXiv  Detail & Related papers  (2020-11-17T12:52:18Z)
• SRDCNN: Strongly Regularized Deep Convolution Neural Network Architecture for Time-series Sensor Signal Classification Tasks [4.950427992960756]
  We present SRDCNN: Strongly Regularized Deep Convolution Neural Network (DCNN) based deep architecture to perform time series classification tasks. The novelty of the proposed approach is that the network weights are regularized by both L1 and L2 norm penalties.
  arXiv  Detail & Related papers  (2020-07-14T08:42:39Z)

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.