Enhancing Transformer Efficiency for Multivariate Time Series Classification

• URL: http://arxiv.org/abs/2203.14472v1
• Date: Mon, 28 Mar 2022 03:25:19 GMT
• Title: Enhancing Transformer Efficiency for Multivariate Time Series Classification
• Authors: Yuqing Wang, Yun Zhao, Linda Petzold
• Abstract summary: We propose a methodology to investigate the relationship between model efficiency and accuracy, as well as its complexity. Comprehensive experiments on benchmark MTS datasets illustrate the effectiveness of our method.
• Score: 12.128991867050487
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Most current multivariate time series (MTS) classification algorithms focus on improving the predictive accuracy. However, for large-scale (either high-dimensional or long-sequential) time series (TS) datasets, there is an additional consideration: to design an efficient network architecture to reduce computational costs such as training time and memory footprint. In this work we propose a methodology based on module-wise pruning and Pareto analysis to investigate the relationship between model efficiency and accuracy, as well as its complexity. Comprehensive experiments on benchmark MTS datasets illustrate the effectiveness of our method.

Related papers

• Temporal Streaming Batch Principal Component Analysis for Time Series Classification [4.622165486890317]
  We propose a principal component analysis (PCA)-based temporal streaming compression and dimensionality reduction algorithm for time series data. Our method demonstrates a trend of increasing effectiveness as sequence length grows.
  arXiv  Detail & Related papers  (2024-10-28T08:11:17Z)
• TSI-Bench: Benchmarking Time Series Imputation [52.27004336123575]
  TSI-Bench is a comprehensive benchmark suite for time series imputation utilizing deep learning techniques. The TSI-Bench pipeline standardizes experimental settings to enable fair evaluation of imputation algorithms. TSI-Bench innovatively provides a systematic paradigm to tailor time series forecasting algorithms for imputation purposes.
  arXiv  Detail & Related papers  (2024-06-18T16:07:33Z)
• SMORE: Similarity-based Hyperdimensional Domain Adaptation for Multi-Sensor Time Series Classification [17.052624039805856]
  We propose SMORE, a novel resource-efficient domain adaptation (DA) algorithm for multi-sensor time series classification. SMORE achieves on average 1.98% higher accuracy than state-of-the-art (SOTA) DNN-based DA algorithms with 18.81x faster training and 4.63x faster inference.
  arXiv  Detail & Related papers  (2024-02-20T18:48:49Z)
• Embedded feature selection in LSTM networks with multi-objective evolutionary ensemble learning for time series forecasting [49.1574468325115]
  We present a novel feature selection method embedded in Long Short-Term Memory networks. Our approach optimize the weights and biases of the LSTM in a partitioned manner. Experimental evaluations on air quality time series data from Italy and southeast Spain demonstrate that our method substantially improves the ability generalization of conventional LSTMs.
  arXiv  Detail & Related papers  (2023-12-29T08:42:10Z)
• Multi-scale Transformer Pyramid Networks for Multivariate Time Series Forecasting [8.739572744117634]
  We introduce a dimension invariant embedding technique that captures short-term temporal dependencies. We present a novel Multi-scale Transformer Pyramid Network (MTPNet) specifically designed to capture temporal dependencies at multiple unconstrained scales.
  arXiv  Detail & Related papers  (2023-08-23T06:40:05Z)
• FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification [53.55504611255664]
  FormerTime is a hierarchical representation model for improving the classification capacity for the multivariate time series classification task. It exhibits three aspects of merits: (1) learning hierarchical multi-scale representations from time series data, (2) inheriting the strength of both transformers and convolutional networks, and (3) tacking the efficiency challenges incurred by the self-attention mechanism.
  arXiv  Detail & Related papers  (2023-02-20T07:46:14Z)
• MTSMAE: Masked Autoencoders for Multivariate Time-Series Forecasting [6.497816402045097]
  We present an self-supervised pre-training approach based on Masked Autoencoders (MAE), called MTSMAE, which can improve the performance significantly over supervised learning without pre-training.
  arXiv  Detail & Related papers  (2022-10-04T03:06:21Z)
• Multi-scale Attention Flow for Probabilistic Time Series Forecasting [68.20798558048678]
  We propose a novel non-autoregressive deep learning model, called Multi-scale Attention Normalizing Flow(MANF) Our model avoids the influence of cumulative error and does not increase the time complexity. Our model achieves state-of-the-art performance on many popular multivariate datasets.
  arXiv  Detail & Related papers  (2022-05-16T07:53:42Z)
• Robust Augmentation for Multivariate Time Series Classification [20.38907456958682]
  We show that the simple methods of cutout, cutmix, mixup, and window warp improve the robustness and overall performance. We show that the InceptionTime network with augmentation improves accuracy by 1% to 45% in 18 different datasets.
  arXiv  Detail & Related papers  (2022-01-27T18:57:49Z)
• Adaptive Anomaly Detection for Internet of Things in Hierarchical Edge Computing: A Contextual-Bandit Approach [81.5261621619557]
  We propose an adaptive anomaly detection scheme with hierarchical edge computing (HEC) We first construct multiple anomaly detection DNN models with increasing complexity, and associate each of them to a corresponding HEC layer. Then, we design an adaptive model selection scheme that is formulated as a contextual-bandit problem and solved by using a reinforcement learning policy network.
  arXiv  Detail & Related papers  (2021-08-09T08:45:47Z)
• 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)

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.