# United We Pretrain, Divided We Fail! Representation Learning for Time Series by Pretraining on 75 Datasets at Once

arXiv: https://arxiv.org/abs/2402.15404 · HTML: https://mlsanity.com/paper/2402.15404/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 23 Feb 2024.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [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)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [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)
- [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://mlsanity.com/paper/1905.11001/) (2019)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding](https://mlsanity.com/paper/2106.00750/) (2021)
- [An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks](https://mlsanity.com/paper/2007.15951/) (2020)
- [SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling](https://mlsanity.com/paper/2302.00861/) (2023)
- [Lightweight, Pre-trained Transformers for Remote Sensing Timeseries](https://mlsanity.com/paper/2304.14065/) (2023)
- [Voice2Series: Reprogramming Acoustic Models for Time Series Classification](https://mlsanity.com/paper/2106.09296/) (2021)
- [Exploring Contrastive Learning in Human Activity Recognition for Healthcare](https://mlsanity.com/paper/2011.11542/) (2020)
- [Ti-MAE: Self-Supervised Masked Time Series Autoencoders](https://mlsanity.com/paper/2301.08871/) (2023)
- [Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Series](https://mlsanity.com/paper/2203.09270/) (2022)
- [A Survey on Time-Series Pre-Trained Models](https://mlsanity.com/paper/2305.10716/) (2023)
- [TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders](https://mlsanity.com/paper/2303.00320/) (2023)
- [ConvTimeNet: A Pre-trained Deep Convolutional Neural Network for Time Series Classification](https://mlsanity.com/paper/1904.12546/) (2019)
- [Multi-view self-supervised learning for multivariate variable-channel time series](https://mlsanity.com/paper/2307.09614/) (2023)
- [PAITS: Pretraining and Augmentation for Irregularly-Sampled Time Series](https://mlsanity.com/paper/2308.13703/) (2023)
- [LEAVES: Learning Views for Time-Series Biobehavioral Data in Contrastive Learning](https://mlsanity.com/paper/2210.07340/) (2022)

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

- [xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories](https://mlsanity.com/paper/2410.16928/) (2024)
- [Forecasting Company Fundamentals](https://mlsanity.com/paper/2411.05791/) (2024)

## Abstract (arXiv)

In natural language processing and vision, pretraining is utilized to learn effective representations. Unfortunately, the success of pretraining does not easily carry over to time series due to potential mismatch between sources and target. Actually, common belief is that multi-dataset pretraining does not work for time series! Au contraire, we introduce a new self-supervised contrastive pretraining approach to learn one encoding from many unlabeled and diverse time series datasets, so that the single learned representation can then be reused in several target domains for, say, classification. Specifically, we propose the XD-MixUp interpolation method and the Soft Interpolation Contextual Contrasting (SICC) loss. Empirically, this outperforms both supervised training and other self-supervised pretraining methods when finetuning on low-data regimes. This disproves the common belief: We can actually learn from multiple time series datasets, even from 75 at once.