Multitask Learning for Time Series Data with 2D Convolution
Not on the map. Why?
Abstract (arXiv)
Multitask learning (MTL) aims to develop a unified model that can handle a set of closely related tasks simultaneously. By optimizing the model across multiple tasks, MTL generally surpasses its non-MTL counterparts in terms of generalizability. Although MTL has been extensively researched in various domains such as computer vision, natural language processing, and recommendation systems, its application to time series data has received limited attention. In this paper, we investigate the application of MTL to the time series classification (TSC) problem. However, when we integrate the state-of-the-art 1D convolution-based TSC model with MTL, the performance of the TSC model actually deteriorates. By comparing the 1D convolution-based models with the Dynamic Time Warping (DTW) distance function, it appears that the underwhelming results stem from the limited expressive power of the 1D convolutional layers. To overcome this challenge, we propose a novel design for a 2D convolution-based model that enhances the model's expressiveness. Leveraging this advantage, our proposed method outperforms competing approaches on both the UCR Archive and an industrial transaction TSC dataset.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 25 of its 39 references that are in the map. First posted on arXiv 5 Oct 2023.
Builds on
25 of 39 references.
References · 25
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2017A Survey on Multi-Task Learningcited by 840
- 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
- 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
- 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 803
- 2018Deep learning for time series classification: a reviewcited by 576
- 2018End-to-End Multi-Task Learning with Attentioncited by 534
- 2016Cross-stitch Networks for Multi-task Learningcited by 467
- 2018The UCR Time Series Archivecited by 431
- 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 360
- 2019Multi-Task Deep Neural Networks for Natural Language Understandingcited by 350
13 more
- 2017Soft-DTW: a Differentiable Loss Function for Time-Seriescited by 271
- 2019AdaShare: Learning What To Share For Efficient Deep Multi-Task Learningcited by 160
- 2018NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reductioncited by 127
- 2021HIVE-COTE 2.0: a new meta ensemble for time series classificationcited by 118
- 2020Learning to Branch for Multi-Task Learningcited by 115
- 2016Multi-Scale Convolutional Neural Networks for Time Series Classificationcited by 99
- 2016Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classificationcited by 93
- 2020MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learningcited by 50
- 2022Embedding Compression with Hashing for Efficient Representation Learning in Large-Scale Graphcited by 10
- 2020A Comprehensive Evaluation of Multi-task Learning and Multi-task Pre-training on EHR Time-series Datacited by 8
- 2020Merchant Category Identification Using Credit Card Transactionscited by 8
- 2020Multi-future Merchant Transaction Predictioncited by 2
- 2021Online Multi-horizon Transaction Metric Estimation with Multi-modal Learning in Payment Networkscited by 2
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.