# Evaluating Temporal Plasticity in Foundation Time Series Models for Incremental Fine-tuning

arXiv: https://arxiv.org/abs/2504.14677 · HTML: https://mlsanity.com/paper/2504.14677/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 20 Apr 2025.

## Builds on (most cited first, 21 of 21)

- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [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)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019](https://mlsanity.com/paper/1911.13288/) (2019)
- [Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding](https://mlsanity.com/paper/2106.00750/) (2021)
- [The Dormant Neuron Phenomenon in Deep Reinforcement Learning](https://mlsanity.com/paper/2302.12902/) (2023)
- [Maintaining Plasticity in Continual Learning via Regenerative Regularization](https://mlsanity.com/paper/2308.11958/) (2023)
- [MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2401.00423/) (2023)
- [Scaling-laws for Large Time-series Models](https://mlsanity.com/paper/2405.13867/) (2024)

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

- [Foundation vs. Specialized Models: Evaluating Catastrophic Forgetting in Continual Time Series Forecasting](https://mlsanity.com/paper/2510.00809/) (2025)
- [CurLL: A Developmental Framework to Evaluate Continual Learning in Language Models](https://mlsanity.com/paper/2510.13008/) (2025)

## Abstract (arXiv)

Time series foundation models excel at diverse time series forecasting tasks, but their capacity for continuous improvement through incremental learning remains unexplored. We present the first comprehensive study investigating these models' temporal plasticity - their ability to progressively enhance performance through continual learning while maintaining existing capabilities. Through experiments on real-world datasets exhibiting distribution shifts, we evaluate both conventional deep learning models and foundation models using a novel continual learning framework. Our findings reveal that while traditional models struggle with performance deterioration during incremental fine-tuning, foundation models like Time-MoE and Chronos demonstrate sustained improvement in predictive accuracy. This suggests that optimizing foundation model fine-tuning strategies may be more valuable than developing domain-specific small models. Our research introduces new evaluation methodologies and insights for developing foundation time series models with robust continuous learning capabilities.