# A Comprehensive Benchmark of Source-Free Universal Domain Adaptation on Time Series Representations

arXiv: https://arxiv.org/abs/2609.39810 · HTML: https://mlsanity.com/paper/2609.39810/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 18 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [TSLANet: Rethinking Transformers for Time Series Representation Learning](https://mlsanity.com/paper/2404.08472/) (2024)
- [ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data](https://mlsanity.com/paper/2203.08321/) (2022)
- [Upcycling Models under Domain and Category Shift](https://mlsanity.com/paper/2303.07110/) (2023)
- [LEAD: Learning Decomposition for Source-free Universal Domain Adaptation](https://mlsanity.com/paper/2403.03421/) (2024)
- [UMAD: Universal Model Adaptation under Domain and Category Shift](https://mlsanity.com/paper/2112.08553/) (2021)
- [Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations](https://mlsanity.com/paper/2405.20082/) (2024)
- [GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning](https://mlsanity.com/paper/2403.14410/) (2024)
- [Deep Joint Distribution Optimal Transport for Universal Domain Adaptation on Time Series](https://mlsanity.com/paper/2503.11217/) (2025)
- [Universal Domain Adaptation Benchmark for Time Series Data Representation](https://mlsanity.com/paper/2505.17899/) (2025)

## Abstract (arXiv)

Source-Free Universal Domain Adaptation (SF-UniDA) extends Universal Domain Adaptation by removing access to source data at adaptation time while still handling label-set mismatches between domains. Despite growing interest in this setting for image data, no benchmark exists for time series, which are more challenging. We present the first SF-UniDA benchmark on time series. In addition, we provide the first study of pretrained foundation models as feature extractors for time series domain adaptation. In this context, we identify a critical and previously underexplored limitation of all existing SF-UniDA methods: the inference threshold for unknown-sample rejection is highly sensitive. We address this by proposing a plug-in auto-thresholding module that can be integrated into any SF-UniDA method. Experiments on three well-known time series datasets confirm the suitability of this module. They also highlight that foundation models do not systematically outperform classical backbones and that SF-UniDA tailored for time series is yet to be developed.