# Temporal Source Recovery for Time-Series Source-Free Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2409.19635 · HTML: https://mlsanity.com/paper/2409.19635/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 73 references that are in the map.
- First posted on arXiv 29 Sep 2024.

## Builds on (most cited first, 30 of 42)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [Time-Series Representation Learning via Temporal and Contextual Contrasting](https://mlsanity.com/paper/2106.14112/) (2021)
- [Foundation Models for Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2403.14735/) (2024)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2110.03374/) (2021)
- [Correlation Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1612.01939/) (2016)
- [A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection](https://mlsanity.com/paper/2307.03759/) (2023)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation](https://mlsanity.com/paper/2205.04183/) (2022)
- [Domain Impression: A Source Data Free Domain Adaptation Method](https://mlsanity.com/paper/2102.09003/) (2021)
- [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)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Unsupervised Multi-source Domain Adaptation Without Access to Source Data](https://mlsanity.com/paper/2104.01845/) (2021)
- [Domain Adaptation for Time Series Under Feature and Label Shifts](https://mlsanity.com/paper/2302.03133/) (2023)
- [Active Learning for Domain Adaptation: An Energy-Based Approach](https://mlsanity.com/paper/2112.01406/) (2021)
- [Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning](https://mlsanity.com/paper/2211.06612/) (2022)
- [Time Series Domain Adaptation via Sparse Associative Structure Alignment](https://mlsanity.com/paper/2012.11797/) (2020)
- [Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing](https://mlsanity.com/paper/2110.15128/) (2021)
- [ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data](https://mlsanity.com/paper/2203.08321/) (2022)
- [Contrastive Learning for Unsupervised Domain Adaptation of Time Series](https://mlsanity.com/paper/2206.06243/) (2022)
- [On Minimum Discrepancy Estimation for Deep Domain Adaptation](https://mlsanity.com/paper/1901.00282/) (2019)
- [ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation](https://mlsanity.com/paper/2205.14566/) (2022)
- [Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation](https://mlsanity.com/paper/2109.04015/) (2021)
- [Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift](https://mlsanity.com/paper/2204.03342/) (2022)

## Built on by (most cited first, 4 of 4)

- [Federated Learning with MMD-based Early Stopping for Adaptive GNSS Interference Classification](https://mlsanity.com/paper/2410.15681/) (2024)
- [Temporal Restoration and Spatial Rewiring for Source-Free Multivariate Time Series Domain Adaptation](https://mlsanity.com/paper/2505.21525/) (2025)
- [5G-DIL: Domain Incremental Learning with Similarity-Aware Sampling for Dynamic 5G Indoor Localization](https://mlsanity.com/paper/2505.17684/) (2025)
- [Active Sensing with Meta-Reinforcement Learning for Emitter Localization from RF Observations](https://mlsanity.com/paper/2605.12569/) (2026)

## Abstract (arXiv)

Time-Series (TS) data has grown in importance with the rise of Internet of Things devices like sensors, but its labeling remains costly and complex. While Unsupervised Domain Adaptation (UDAs) offers an effective solution, growing data privacy concerns have led to the development of Source-Free UDA (SFUDAs), enabling model adaptation to target domains without accessing source data. Despite their potential, applying existing SFUDAs to TS data is challenging due to the difficulty of transferring temporal dependencies, an essential characteristic of TS data, particularly in the absence of source samples. Although prior works attempt to address this by specific source pretraining designs, such requirements are often impractical, as source data owners cannot be expected to adhere to particular pretraining schemes. To address this, we propose Temporal Source Recovery (TemSR), a framework that leverages the intrinsic properties of TS data to generate a source-like domain and recover source temporal dependencies. With this domain, TemSR enables dependency transfer to the target domain without accessing source data or relying on source-specific designs, thereby facilitating effective and practical TS-SFUDA. TemSR features a masking recovery optimization process to generate a source-like distribution with restored temporal dependencies. This distribution is further refined through local context-aware regularization to preserve local dependencies, and anchor-based recovery diversity maximization to promote distributional diversity. Together, these components enable effective temporal dependency recovery and facilitate transfer across domains using standard UDA techniques. Extensive experiments across multiple TS tasks demonstrate the effectiveness of TemSR, which even surpasses existing TS-SFUDA methods that require source-specific designs.