# Transferable Time-Series Forecasting under Causal Conditional Shift

arXiv: https://arxiv.org/abs/2111.03422 · HTML: https://mlsanity.com/paper/2111.03422/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 59 references that are in the map.
- First posted on arXiv 5 Nov 2021.

## Builds on (most cited first, 25 of 25)

- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [A Recurrent Latent Variable Model for Sequential Data](https://mlsanity.com/paper/1506.02216/) (2015)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [Bridging Theory and Algorithm for Domain Adaptation](https://mlsanity.com/paper/1904.05801/) (2019)
- [Unrolled Generative Adversarial Networks](https://mlsanity.com/paper/1611.02163/) (2016)
- [HP-GAN: Probabilistic 3D human motion prediction via GAN](https://mlsanity.com/paper/1711.09561/) (2017)
- [Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data](https://mlsanity.com/paper/2006.10833/) (2020)
- [Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation](https://mlsanity.com/paper/2010.04647/) (2020)
- [Domain Adaptation for Time Series Forecasting via Attention Sharing](https://mlsanity.com/paper/2102.06828/) (2021)
- [Learning Disentangled Semantic Representation for Domain Adaptation](https://mlsanity.com/paper/2012.11807/) (2020)
- [Time Series Domain Adaptation via Sparse Associative Structure Alignment](https://mlsanity.com/paper/2012.11797/) (2020)
- [Interpretable Models for Granger Causality Using Self-explaining Neural Networks](https://mlsanity.com/paper/2101.07600/) (2021)
- [Domain Adaptation as a Problem of Inference on Graphical Models](https://mlsanity.com/paper/2002.03278/) (2020)
- [Graph Domain Adaptation: A Generative View](https://mlsanity.com/paper/2106.07482/) (2021)
- [Remaining Useful Lifetime Prediction via Deep Domain Adaptation](https://mlsanity.com/paper/1907.07480/) (2019)
- [Aggregating From Multiple Target-Shifted Sources](https://mlsanity.com/paper/2105.04051/) (2021)
- [Semi-Supervised Disentangled Framework for Transferable Named Entity Recognition](https://mlsanity.com/paper/2012.11805/) (2020)
- [Joint modeling of multiple time series via the beta process with application to motion capture segmentation](https://mlsanity.com/paper/1308.4747/) (2013)
- [Causal Mechanism Transfer Network for Time Series Domain Adaptation in Mechanical Systems](https://mlsanity.com/paper/1910.06761/) (2019)
- [Self-supervised Multi-scale Consistency for Weakly Supervised Segmentation Learning](https://mlsanity.com/paper/2108.11900/) (2021)

## Built on by (most cited first, 18 of 18)

- [Temporally Disentangled Representation Learning](https://mlsanity.com/paper/2210.13647/) (2022)
- [A Survey on Time-Series Pre-Trained Models](https://mlsanity.com/paper/2305.10716/) (2023)
- [Subspace Identification for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2310.04723/) (2023)
- [On the Identification of Temporally Causal Representation with Instantaneous Dependence](https://mlsanity.com/paper/2405.15325/) (2024)
- [Out-of-Distribution Generalization in Time Series: A Survey](https://mlsanity.com/paper/2503.13868/) (2025)
- [Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2211.10412/) (2022)
- [PGODE: Towards High-quality System Dynamics Modeling](https://mlsanity.com/paper/2311.06554/) (2023)
- [Time-Series Domain Adaptation via Sparse Associative Structure Alignment: Learning Invariance and Variance](https://mlsanity.com/paper/2205.03554/) (2022)
- [Time Series Forecasting with Hypernetworks Generating Parameters in Advance](https://mlsanity.com/paper/2211.12034/) (2022)
- [Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning](https://mlsanity.com/paper/2404.14073/) (2024)
- [TNPAR: Topological Neural Poisson Auto-Regressive Model for Learning Granger Causal Structure from Event Sequences](https://mlsanity.com/paper/2306.14114/) (2023)
- [SeqFusion: Sequential Fusion of Pre-Trained Models for Zero-Shot Time-Series Forecasting](https://mlsanity.com/paper/2503.02836/) (2025)
- [Nonstationary Time Series Forecasting via Unknown Distribution Adaptation](https://mlsanity.com/paper/2402.12767/) (2024)
- [Robust Multivariate Time Series Forecasting against Intra- and Inter-Series Transitional Shift](https://mlsanity.com/paper/2407.13194/) (2024)
- [Time Series Domain Adaptation via Latent Invariant Causal Mechanism](https://mlsanity.com/paper/2502.16637/) (2025)
- [Integrating Quantum-Classical Attention in Patch Transformers for Enhanced Time Series Forecasting](https://mlsanity.com/paper/2504.00068/) (2025)
- [Towards Causal Relationship in Indefinite Data: Baseline Model and New Datasets](https://mlsanity.com/paper/2401.08221/) (2024)
- [Liquid Gated Attention](https://mlsanity.com/paper/2608.30695/) (2026)

## Abstract (arXiv)

This paper focuses on the problem of semi-supervised domain adaptation for time-series forecasting, which is underexplored in literatures, despite being often encountered in practice. Existing methods on time-series domain adaptation mainly follow the paradigm designed for the static data, which cannot handle domain-specific complex conditional dependencies raised by data offset, time lags, and variant data distributions. In order to address these challenges, we analyze variational conditional dependencies in time-series data and find that the causal structures are usually stable among domains, and further raise the causal conditional shift assumption. Enlightened by this assumption, we consider the causal generation process for time-series data and propose an end-to-end model for the semi-supervised domain adaptation problem on time-series forecasting. Our method can not only discover the Granger-Causal structures among cross-domain data but also address the cross-domain time-series forecasting problem with accurate and interpretable predicted results. We further theoretically analyze the superiority of the proposed method, where the generalization error on the target domain is bounded by the empirical risks and by the discrepancy between the causal structures from different domains. Experimental results on both synthetic and real data demonstrate the effectiveness of our method for the semi-supervised domain adaptation method on time-series forecasting.