# Multitask Learning for Time Series Data with 2D Convolution

arXiv: https://arxiv.org/abs/2310.03925 · HTML: https://mlsanity.com/paper/2310.03925/

## 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 (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [Cross-stitch Networks for Multi-task Learning](https://mlsanity.com/paper/1604.03539/) (2016)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [Multi-Task Deep Neural Networks for Natural Language Understanding](https://mlsanity.com/paper/1901.11504/) (2019)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning](https://mlsanity.com/paper/1911.12423/) (2019)
- [NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction](https://mlsanity.com/paper/1801.08297/) (2018)
- [HIVE-COTE 2.0: a new meta ensemble for time series classification](https://mlsanity.com/paper/2104.07551/) (2021)
- [Learning to Branch for Multi-Task Learning](https://mlsanity.com/paper/2006.01895/) (2020)
- [Multi-Scale Convolutional Neural Networks for Time Series Classification](https://mlsanity.com/paper/1603.06995/) (2016)
- [Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification](https://mlsanity.com/paper/1611.05377/) (2016)
- [MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning](https://mlsanity.com/paper/2003.14058/) (2020)
- [Embedding Compression with Hashing for Efficient Representation Learning in Large-Scale Graph](https://mlsanity.com/paper/2208.05648/) (2022)
- [A Comprehensive Evaluation of Multi-task Learning and Multi-task Pre-training on EHR Time-series Data](https://mlsanity.com/paper/2007.10185/) (2020)
- [Merchant Category Identification Using Credit Card Transactions](https://mlsanity.com/paper/2011.02602/) (2020)
- [Multi-future Merchant Transaction Prediction](https://mlsanity.com/paper/2007.05303/) (2020)
- [Online Multi-horizon Transaction Metric Estimation with Multi-modal Learning in Payment Networks](https://mlsanity.com/paper/2109.10020/) (2021)

## Built on by (most cited first, 2 of 2)

- [RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data](https://mlsanity.com/paper/2402.10487/) (2024)
- [Ego-Network Transformer for Subsequence Classification in Time Series Data](https://mlsanity.com/paper/2311.02561/) (2023)

## 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.