# Learning Compositional Transferability of Time Series for Source-Free Domain Adaptation

arXiv: https://arxiv.org/abs/2504.14994 · HTML: https://mlsanity.com/paper/2504.14994/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Builds on (most cited first, 28 of 28)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1607.03516/) (2016)
- [Correlation Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1612.01939/) (2016)
- [TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation](https://mlsanity.com/paper/2302.05155/) (2023)
- [Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation](https://mlsanity.com/paper/2205.04183/) (2022)
- [HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1912.11976/) (2019)
- [Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data](https://mlsanity.com/paper/2005.10996/) (2020)
- [Time Series as Images: Vision Transformer for Irregularly Sampled Time Series](https://mlsanity.com/paper/2303.12799/) (2023)
- [SoTTA: Robust Test-Time Adaptation on Noisy Data Streams](https://mlsanity.com/paper/2310.10074/) (2023)
- [Domain Adaptation for Time Series Under Feature and Label Shifts](https://mlsanity.com/paper/2302.03133/) (2023)
- [TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning](https://mlsanity.com/paper/2312.15709/) (2023)
- [Time Series Domain Adaptation via Sparse Associative Structure Alignment](https://mlsanity.com/paper/2012.11797/) (2020)
- [ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data](https://mlsanity.com/paper/2203.08321/) (2022)
- [On Minimum Discrepancy Estimation for Deep Domain Adaptation](https://mlsanity.com/paper/1901.00282/) (2019)
- [MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series](https://mlsanity.com/paper/2212.01141/) (2022)
- [CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learning](https://mlsanity.com/paper/2109.14778/) (2021)
- [SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity Recognition](https://mlsanity.com/paper/2212.00724/) (2022)
- [FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification](https://mlsanity.com/paper/2302.09818/) (2023)
- [Source-Free Domain Adaptation with Temporal Imputation for Time Series Data](https://mlsanity.com/paper/2307.07542/) (2023)
- [Toward Interpretable Sleep Stage Classification Using Cross-Modal Transformers](https://mlsanity.com/paper/2208.06991/) (2022)
- [Sparse Binary Transformers for Multivariate Time Series Modeling](https://mlsanity.com/paper/2308.04637/) (2023)
- [POND: Multi-Source Time Series Domain Adaptation with Information-Aware Prompt Tuning](https://mlsanity.com/paper/2312.12276/) (2023)

## Abstract (arXiv)

Domain adaptation is challenging for time series classification due to the highly dynamic nature. This study tackles the most difficult subtask when both target labels and source data are inaccessible, namely, source-free domain adaptation. To reuse the classification backbone pre-trained on source data, time series reconstruction is a sound solution that aligns target and source time series by minimizing the reconstruction errors of both. However, simply fine-tuning the source pre-trained reconstruction model on target data may lose the learnt priori, and it struggles to accommodate domain varying temporal patterns in a single encoder-decoder. Therefore, this paper tries to disentangle the composition of domain transferability by using a compositional architecture for time series reconstruction. Here, the preceding component is a U-net frozen since pre-trained, the output of which during adaptation is the initial reconstruction of a given target time series, acting as a coarse step to prompt the subsequent finer adaptation. The following pipeline for finer adaptation includes two parallel branches: The source replay branch using a residual link to preserve the output of U-net, and the offset compensation branch that applies an additional autoencoder (AE) to further warp U-net's output. By deploying a learnable factor on either branch to scale their composition in the final output of reconstruction, the data transferability is disentangled and the learnt reconstructive capability from source data is retained. During inference, aside from the batch-level optimization in the training, we search at test time stability-aware rescaling of source replay branch to tolerate instance-wise variation. The experimental results show that such compositional architecture of time series reconstruction leads to SOTA performance on 3 widely used benchmarks.