# Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer

arXiv: https://arxiv.org/abs/2405.17478 · HTML: https://mlsanity.com/paper/2405.17478/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 56 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [The UEA multivariate time series classification archive, 2018](https://mlsanity.com/paper/1811.00075/) (2018)
- [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https://mlsanity.com/paper/2106.09305/) (2021)
- [Monash Time Series Forecasting Archive](https://mlsanity.com/paper/2105.06643/) (2021)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods](https://mlsanity.com/paper/2403.20150/) (2024)
- [A Multi-Horizon Quantile Recurrent Forecaster](https://mlsanity.com/paper/1711.11053/) (2017)
- [TimeGPT-1](https://mlsanity.com/paper/2310.03589/) (2023)
- [SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling](https://mlsanity.com/paper/2302.00861/) (2023)
- [ForecastPFN: Synthetically-Trained Zero-Shot Forecasting](https://mlsanity.com/paper/2311.01933/) (2023)
- [Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting](https://mlsanity.com/paper/2402.05956/) (2024)
- [Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series](https://mlsanity.com/paper/2310.14017/) (2023)
- [AutoCTS: Automated Correlated Time Series Forecasting -- Extended Version](https://mlsanity.com/paper/2112.11174/) (2021)
- [A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Data](https://mlsanity.com/paper/2404.14999/) (2024)
- [Learning to Embed Time Series Patches Independently](https://mlsanity.com/paper/2312.16427/) (2023)

## Built on by (most cited first, 30 of 32)

- [CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching](https://mlsanity.com/paper/2410.12261/) (2024)
- [Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective](https://mlsanity.com/paper/2510.14510/) (2025)
- [Aurora: Towards Universal Generative Multimodal Time Series Forecasting](https://mlsanity.com/paper/2509.22295/) (2025)
- [LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimization](https://mlsanity.com/paper/2503.08271/) (2025)
- [BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models](https://mlsanity.com/paper/2505.17871/) (2025)
- [Rethinking Evaluation in the Era of Time Series Foundation Models: (Un)known Information Leakage Challenges](https://mlsanity.com/paper/2510.13654/) (2025)
- [AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting](https://mlsanity.com/paper/2511.08947/) (2025)
- [OTIS: Learning High-Quality Time Series Features With Tiny Encoders](https://mlsanity.com/paper/2410.07299/) (2024)
- [K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2505.23017/) (2025)
- [User-friendly Foundation Model Adapters for Multivariate Time Series Classification](https://mlsanity.com/paper/2409.12264/) (2024)
- [FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting](https://mlsanity.com/paper/2512.14253/) (2025)
- [Empowering Time Series Analysis with Large-Scale Multimodal Pretraining](https://mlsanity.com/paper/2602.05646/) (2026)
- [EXAONE Finance 1.0: An Attention-free Time Series Foundation Model for Financial Time Series](https://mlsanity.com/paper/2609.04239/) (2026)
- [Data Driven Decision Making with Time Series and Spatio-temporal Data](https://mlsanity.com/paper/2503.08473/) (2025)
- [Bridging Distribution Gaps in Time Series Foundation Model Pretraining with Prototype-Guided Normalization](https://mlsanity.com/paper/2504.10900/) (2025)
- [Towards Measuring and Modeling Geometric Structures in Time Series Forecasting via Image Modality](https://mlsanity.com/paper/2507.23253/) (2025)
- [Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting](https://mlsanity.com/paper/2509.15105/) (2025)
- [Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Models](https://mlsanity.com/paper/2601.12083/) (2026)
- [Unify and Anchor: A Context-Aware Transformer for Cross-Domain Time Series Forecasting](https://mlsanity.com/paper/2503.01157/) (2025)
- [Time Series Forecasting Through the Lens of Dynamics](https://mlsanity.com/paper/2507.15774/) (2025)
- [TimeRadar: A Domain-Rotatable Foundation Model for Time Series Anomaly Detection](https://mlsanity.com/paper/2602.19068/) (2026)
- [Olivia: Harmonizing Time Series Foundation Models with Power Spectral Density](https://mlsanity.com/paper/2605.17340/) (2026)
- [QiYao-M: Multimodal Time Series Foundation Model with Role-Aware Modeling of Endogenous and Exogenous Modalities](https://mlsanity.com/paper/2609.34842/) (2026)
- [Invariant Representation Learning for Source-Free Time Series Forecasting with LLM-Centric Proxy Denoising](https://mlsanity.com/paper/2510.05589/) (2025)
- [VLBM: Variational Latent Basis Modeling for OOD Robust Multivariate Time Series Forecasting](https://mlsanity.com/paper/2606.02138/) (2026)
- [TimeBlocks: Foundational and Continual Time-Series Blockbase -- Extended Version](https://mlsanity.com/paper/2606.02142/) (2026)
- [REGAIN: REconciliation GAIN-driven Auxiliary Direction Learning](https://mlsanity.com/paper/2606.04380/) (2026)
- [Towards a Unified Generative Model for Scarce Time Series with Domain Experts](https://mlsanity.com/paper/2606.15172/) (2026)
- [When AI Designs AI: Innovation or Imitation?](https://mlsanity.com/paper/2608.17471/) (2026)
- [QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization](https://mlsanity.com/paper/2609.20156/) (2026)

## Abstract (arXiv)

With the growing availability of multi-domain time series data, there is an increasing demand for general forecasting models pre-trained on multi-source datasets to support diverse downstream prediction scenarios. Existing time series foundation models primarily focus on scaling up pre-training datasets and model sizes to enhance generalization performance. In this paper, we take a different approach by addressing two critical aspects of general forecasting models: (1) how to derive unified representations from heterogeneous multi-domain time series data, and (2) how to effectively capture domain-specific features to enable adaptive transfer across various downstream scenarios. To address the first aspect, we propose Decomposed Frequency Learning as the pre-training task, which leverages frequency-based masking and reconstruction to decompose coupled semantic information in time series, resulting in unified representations across domains. For the second aspect, we introduce the Time Series Register, which captures domain-specific representations during pre-training and enhances adaptive transferability to downstream tasks. Our model achieves the state-of-the-art forecasting performance on seven real-world benchmarks, demonstrating remarkable few-shot and zero-shot capabilities.