# Cross-Domain Pre-training with Language Models for Transferable Time Series Representations

arXiv: https://arxiv.org/abs/2403.12372 · HTML: https://mlsanity.com/paper/2403.12372/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 50 references that are in the map.
- First posted on arXiv 19 Mar 2024.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Transformers in Time Series: A Survey](https://mlsanity.com/paper/2202.07125/) (2022)
- [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)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [Time-Series Representation Learning via Temporal and Contextual Contrasting](https://mlsanity.com/paper/2106.14112/) (2021)
- [Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding](https://mlsanity.com/paper/2106.00750/) (2021)
- [Bake off redux: a review and experimental evaluation of recent time series classification algorithms](https://mlsanity.com/paper/2304.13029/) (2023)
- [Self-Supervised Transformer for Sparse and Irregularly Sampled Multivariate Clinical Time-Series](https://mlsanity.com/paper/2107.14293/) (2021)
- [A Time Series Forest for Classification and Feature Extraction](https://mlsanity.com/paper/1302.2277/) (2013)
- [TS-CHIEF: A Scalable and Accurate Forest Algorithm for Time Series Classification](https://mlsanity.com/paper/1906.10329/) (2019)
- [Gated Transformer Networks for Multivariate Time Series Classification](https://mlsanity.com/paper/2103.14438/) (2021)
- [Understanding Masked Image Modeling via Learning Occlusion Invariant Feature](https://mlsanity.com/paper/2208.04164/) (2022)
- [Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights](https://mlsanity.com/paper/2305.15036/) (2023)
- [Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models' Transferability](https://mlsanity.com/paper/2103.07162/) (2021)

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

- [From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization](https://mlsanity.com/paper/2508.09191/) (2025)
- [Time Series Analysis in Frequency Domain: A Survey of Open Challenges, Opportunities and Benchmarks](https://mlsanity.com/paper/2504.07099/) (2025)
- [TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Models](https://mlsanity.com/paper/2411.15737/) (2024)
- [Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification](https://mlsanity.com/paper/2410.18686/) (2024)
- [Leveraging Multi-AI Agents for Cross-Domain Knowledge Discovery](https://mlsanity.com/paper/2404.08511/) (2024)
- [DisenTS: Disentangled Channel Evolving Pattern Modeling for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2410.22981/) (2024)
- [InstructTime++: Time Series Classification with Multimodal Language Modeling via Implicit Feature Enhancement](https://mlsanity.com/paper/2601.14968/) (2026)
- [Bi-level Heterogeneous Learning for Time Series Foundation Models: A Federated Learning Approach](https://mlsanity.com/paper/2604.06727/) (2026)
- [OneCast: Structured Decomposition and Modular Generation for Cross-Domain Time Series Forecasting](https://mlsanity.com/paper/2510.24028/) (2025)
- [CoGenCast: A Coupled Autoregressive-Flow Generative Framework for Time Series Forecasting](https://mlsanity.com/paper/2602.03564/) (2026)
- [Towards a Unified Generative Model for Scarce Time Series with Domain Experts](https://mlsanity.com/paper/2606.15172/) (2026)
- [Predicting the Unpredictable: LLM-powered Long-term Chaotic Time Series Forecasting under Short-term Observations](https://mlsanity.com/paper/2608.29579/) (2026)

## Abstract (arXiv)

Advancements in self-supervised pre-training (SSL) have significantly advanced the field of learning transferable time series representations, which can be very useful in enhancing the downstream task. Despite being effective, most existing works struggle to achieve cross-domain SSL pre-training, missing valuable opportunities to integrate patterns and features from different domains. The main challenge lies in the significant differences in the characteristics of time-series data across different domains, such as variations in the number of channels and temporal resolution scales. To address this challenge, we propose CrossTimeNet, a novel cross-domain SSL learning framework to learn transferable knowledge from various domains to largely benefit the target downstream task. One of the key characteristics of CrossTimeNet is the newly designed time series tokenization module, which could effectively convert the raw time series into a sequence of discrete tokens based on a reconstruction optimization process. Besides, we highlight that predicting a high proportion of corrupted tokens can be very helpful for extracting informative patterns across different domains during SSL pre-training, which has been largely overlooked in past years. Furthermore, unlike previous works, our work treats the pre-training language model (PLM) as the initialization of the encoder network, investigating the feasibility of transferring the knowledge learned by the PLM to the time series area. Through these efforts, the path to cross-domain pre-training of a generic time series model can be effectively paved. We conduct extensive experiments in a real-world scenario across various time series classification domains. The experimental results clearly confirm CrossTimeNet's superior performance.