# Multi-source Transfer Learning of Time Series with a Shapelet-based Distance Measure

arXiv: https://arxiv.org/abs/2609.15148 · HTML: https://mlsanity.com/paper/2609.15148/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 20 of 20)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [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)
- [Timer: Generative Pre-trained Transformers Are Large Time Series Models](https://mlsanity.com/paper/2402.02368/) (2024)
- [LEEP: A New Measure to Evaluate Transferability of Learned Representations](https://mlsanity.com/paper/2002.12462/) (2020)
- [LogME: Practical Assessment of Pre-trained Models for Transfer Learning](https://mlsanity.com/paper/2102.11005/) (2021)
- [An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks](https://mlsanity.com/paper/2007.15951/) (2020)
- [Transferability and Hardness of Supervised Classification Tasks](https://mlsanity.com/paper/1908.08142/) (2019)
- [A Survey on Negative Transfer](https://mlsanity.com/paper/2009.00909/) (2020)
- [UniTS: A Unified Multi-Task Time Series Model](https://mlsanity.com/paper/2403.00131/) (2024)
- [An Information-Theoretic Approach to Transferability in Task Transfer Learning](https://mlsanity.com/paper/2212.10082/) (2022)
- [Transfer learning for time series classification](https://mlsanity.com/paper/1811.01533/) (2018)
- [Self-supervised Autoregressive Domain Adaptation for Time Series Data](https://mlsanity.com/paper/2111.14834/) (2021)
- [Learning Soft Sparse Shapes for Efficient Time-Series Classification](https://mlsanity.com/paper/2505.06892/) (2025)
- [Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variance](https://mlsanity.com/paper/2308.05986/) (2023)
- [A Unified Shape-Aware Foundation Model for Time Series Classification](https://mlsanity.com/paper/2601.06429/) (2026)
- [Model Selection with a Shapelet-based Distance Measure for Multi-source Transfer Learning in Time Series Classification](https://mlsanity.com/paper/2409.20005/) (2024)

## Abstract (arXiv)

Transfer learning is an effective technique for addressing data scarcity in deep learning for time series classification, but its success depends on the selection of source datasets. Conventional transferability estimation methods are often computationally expensive, as they require fully pre-training a model on each potential source dataset to assess its suitability. This paper introduces a novel, training-free source selection method named Shapelet Matching. Our approach first identifies discriminative shapelets from the target and potential source datasets. Then, Shapelet Matching quantifies dataset similarity by comparing the extracted sets of shapelets. To mitigate the risk of negative transfer from selecting an unsuitable single source, we introduce a multi-source transfer learning method. We select several source datasets based on their shapelet-based similarity scores, combine them into a single multi-source dataset, and use this aggregated dataset for pre-training. The model is then fine-tuned on the target task. We evaluated our method on 128 datasets from the UCR Archive using both temporal CNN and Transformer architectures. The empirical results demonstrate that our multi-source pre-training reduces the risk of negative transfer on average. Shapelet Matching achieves the strongest performance for the CNN backbone and remains competitive for patch-based Transformer architectures, while avoiding the cost of pre-training a separate model for every candidate source.