.png){kind=icon}
Return
TRACE: Time SeRies PArameter EffiCient FinE-tuning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.132098.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We propose an efficient fine-tuning method for time series foundation models, termed TRACE: Time Series Parameter Efficient Fine-tuning. While pretrained time series foundation models are gaining popularity, they face the following challenges: (1) Time series data exhibit significant heterogeneity in frequency, channel count, and sequence lengths, necessitating tailored fine-tuning strategies, especially for long-term forecasting. (2) Existing parameter-efficient fine-tuning (PEFT) methods, such as LoRA, are not directly optimized for the unique characteristics of time series data.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
Cited Papers
No cited papers available