# Parametric Augmentation for Time Series Contrastive Learning

arXiv: https://arxiv.org/abs/2402.10434 · HTML: https://mlsanity.com/paper/2402.10434/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 61 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Builds on (most cited first, 30 of 46)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https://mlsanity.com/paper/1907.00235/) (2019)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [A Transformer-based Framework for Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2010.02803/) (2020)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [Time-Series Representation Learning via Temporal and Contextual Contrasting](https://mlsanity.com/paper/2106.14112/) (2021)
- [Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting](https://mlsanity.com/paper/2103.07719/) (2021)
- [Unsupervised Scalable Representation Learning for Multivariate Time Series](https://mlsanity.com/paper/1901.10738/) (2019)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding](https://mlsanity.com/paper/2106.00750/) (2021)
- [Adversarial Graph Augmentation to Improve Graph Contrastive Learning](https://mlsanity.com/paper/2106.05819/) (2021)
- [Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules](https://mlsanity.com/paper/1905.05393/) (2019)
- [CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting](https://mlsanity.com/paper/2202.01575/) (2022)
- [TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2306.09364/) (2023)
- [InfoGCL: Information-Aware Graph Contrastive Learning](https://mlsanity.com/paper/2110.15438/) (2021)

## Built on by (most cited first, 12 of 12)

- [MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with 0.1K Parameters](https://mlsanity.com/paper/2410.02081/) (2024)
- [AimTS: Augmented Series and Image Contrastive Learning for Time Series Classification](https://mlsanity.com/paper/2504.09993/) (2025)
- [FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification](https://mlsanity.com/paper/2505.23181/) (2025)
- [MMFNet: Multi-Scale Frequency Masking Neural Network for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2410.02070/) (2024)
- [How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction](https://mlsanity.com/paper/2507.11161/) (2025)
- [Instruction-based Time Series Editing](https://mlsanity.com/paper/2508.01504/) (2025)
- [Learning Time-Series Representations by Hierarchical Uniformity-Tolerance Latent Balancing](https://mlsanity.com/paper/2510.01658/) (2025)
- [CSRA: Controlled Spectral Residual Augmentation for Robust Sepsis Prediction](https://mlsanity.com/paper/2604.14532/) (2026)
- [CF-JEPA: Mask-free forward prediction with asymmetric encoder utilization for time-series representation learning](https://mlsanity.com/paper/2606.07031/) (2026)
- [MFF-FTNet: Multi-scale Feature Fusion across Frequency and Temporal Domains for Time Series Forecasting](https://mlsanity.com/paper/2411.17382/) (2024)
- [DRAN: A Distribution and Relation Adaptive Network for Spatio-temporal Forecasting](https://mlsanity.com/paper/2504.01531/) (2025)
- [PLanTS: Periodicity-aware Latent-state Representation Learning for Multivariate Time Series](https://mlsanity.com/paper/2509.05478/) (2025)

## Abstract (arXiv)

Modern techniques like contrastive learning have been effectively used in many areas, including computer vision, natural language processing, and graph-structured data. Creating positive examples that assist the model in learning robust and discriminative representations is a crucial stage in contrastive learning approaches. Usually, preset human intuition directs the selection of relevant data augmentations. Due to patterns that are easily recognized by humans, this rule of thumb works well in the vision and language domains. However, it is impractical to visually inspect the temporal structures in time series. The diversity of time series augmentations at both the dataset and instance levels makes it difficult to choose meaningful augmentations on the fly. In this study, we address this gap by analyzing time series data augmentation using information theory and summarizing the most commonly adopted augmentations in a unified format. We then propose a contrastive learning framework with parametric augmentation, AutoTCL, which can be adaptively employed to support time series representation learning. The proposed approach is encoder-agnostic, allowing it to be seamlessly integrated with different backbone encoders. Experiments on univariate forecasting tasks demonstrate the highly competitive results of our method, with an average 6.5% reduction in MSE and 4.7% in MAE over the leading baselines. In classification tasks, AutoTCL achieves a 1.2% increase in average accuracy.