# Convolutional Neural Networks for Time-dependent Classification of Variable-length Time Series

arXiv: https://arxiv.org/abs/2207.03718 · HTML: https://mlsanity.com/paper/2207.03718/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 8 Jul 2022.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [The UEA multivariate time series classification archive, 2018](https://mlsanity.com/paper/1811.00075/) (2018)
- [Time Series Data Imputation: A Survey on Deep Learning Approaches](https://mlsanity.com/paper/2011.11347/) (2020)
- [Self-Attentional Acoustic Models](https://mlsanity.com/paper/1803.09519/) (2018)
- [Learnable Dynamic Temporal Pooling for Time Series Classification](https://mlsanity.com/paper/2104.02577/) (2021)
- [Classifying Variable-Length Audio Files with All-Convolutional Networks and Masked Global Pooling](https://mlsanity.com/paper/1607.02857/) (2016)

## Built on by (most cited first, 1 of 1)

- [Early Classification of Time Series: A Survey and Benchmark](https://mlsanity.com/paper/2406.18332/) (2024)

## Abstract (arXiv)

Time series data are often obtained only within a limited time range due to interruptions during observation process. To classify such partial time series, we need to account for 1) the variable-length data drawn from 2) different timestamps. To address the first problem, existing convolutional neural networks use global pooling after convolutional layers to cancel the length differences. This architecture suffers from the trade-off between incorporating entire temporal correlations in long data and avoiding feature collapse for short data. To resolve this tradeoff, we propose Adaptive Multi-scale Pooling, which aggregates features from an adaptive number of layers, i.e., only the first few layers for short data and more layers for long data. Furthermore, to address the second problem, we introduce Temporal Encoding, which embeds the observation timestamps into the intermediate features. Experiments on our private dataset and the UCR/UEA time series archive show that our modules improve classification accuracy especially on short data obtained as partial time series.