- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes the FedTinyTS three-stage framework to address the issues of high communication overhead and poor model adaptability in federated temporal prediction. Through three steps of compressed transmission, reliable aggregation, and local adaptation, the framework significantly reduces communication volume while maintaining good prediction performance.
Critical strengths
- The amount of data to be transmitted has significantly decreased, by up to several thousand times compared with FedAvg, saving bandwidth and time.
- With just one round trip of data transmission, a shared prediction model can be developed, and each client can adjust its own version to suit local conditions without the need for additional communication.
- This paper is well written and easy to follow.
Critical weaknesses
- The poor performance of the method on the MAE metric indicates significant limitations in predictive performance.
- The compression of temporal data relies on stable data patterns, but it has not been fully validated on data with changing patterns.
- It only uses a simple linear prediction model and cannot capture complex nonlinear relationships in the data, which limits its applicability in various scenarios.
- Without a dedicated privacy protection mechanism, the transmitted statistical information may still reveal information about the original data.
Questions for authors
- Why does FedTinyTS perform worse than some baseline methods in terms of MAE? Are the results still the same when compared under the same training loss function?
- Can FedTinyTS maintain its predictive performance when there are non-stationary features such as obvious trends and sudden changes in the time series? Is there any relevant experimental support?
- Why does FedTinyTS only use a linear prediction model? Does FedTinyTS still have advantages over federated forecasting methods that can handle nonlinear relationships?
- Is it possible for the transmitted statistical information to leak characteristics of a client's original data? Can you provide an experimental assessment of privacy leakage risks?
- In the paper's experiments, personalization is actually performed on the server. If executed on the client side according to the proposed communication protocol, will the communication cost and running time still be consistent with the reported results?
9 comments
W2 & Q2: Non-stationary data with trends or sudden changes.
Thanks for raising this question. Our results support gradual drift and weak non-stationarity represented in the benchmarks, but not abrupt level shifts or sudden structural changes.
(1) The benchmarks are non-stationary. The main results in Section 4 are obtained on these series.
Table R4. Stationarity tests and train-to-test shift per dataset (definitions in (4)):
| Dataset | Series | Non-stationary (ADF or KPSS, 5%) | Median mean shift (train SD) | Series shifting SD | Median KS |
|---|---|---|---|---|---|
| ETH | 14 | 100% | 0.34 | 28.6% | 0.20 |
| Electricity | 321 | 98.1% | 0.13 | 5.6% | 0.11 |
| SolarEnergy | 137 | 100% | 0.20 | 0.0% | 0.09 |
| TW5K | 1,000 | 53.3% | 0.06 | 1.2% | 0.05 |
| Traffic | 862 | 79.1% | 0.08 | 3.3% | 0.07 |
Finding. Most series fail a stationarity test, but their drift is weak (median train/test shift 0.06 to 0.34 SD). These aggregate diagnostics are consistent with locally stationary processes [1, 2], the regime of standard long-term forecasting benchmarks [3], although they do not test stationarity within each window.
(2) Scope of the stationarity assumption. The global least-squares solve does not require global stationarity. However, accurate lag compression relies on approximate lag invariance within each window, corresponding to a weak local-stationarity condition.
(3) Sudden changes are out of scope. Level shifts and similar abrupt changes are usually handled by change detection, windowing or forgetting [6].
(4) Tests. ADF [4] counts a series as non-stationary when , KPSS [5] when . Shift is (test mean train mean) / train SD, and KS is the two-sample Kolmogorov–Smirnov statistic.
(5) Revision. We revised the Conclusion (in red) to state that the scope is weak non-stationarity, with sudden changes such as level shifts outside it.
[1] M. B. Priestley. Evolutionary Spectra and Non-Stationary Processes. JRSS-B, 27(2), 1965.
[2] R. Dahlhaus. Fitting Time Series Models to Nonstationary Processes. Annals of Statistics, 25(1), 1997.
[3] Y. Liu, H. Wu, J. Wang, M. Long. Non-stationary Transformers. NeurIPS, 2022.
[4] S. E. Said, D. A. Dickey. Testing for Unit Roots in ARMA Models of Unknown Order. Biometrika, 71(3), 1984.
[5] D. Kwiatkowski, P. Phillips, P. Schmidt, Y. Shin. Testing the Null Hypothesis of Stationarity. J. Econometrics, 54, 1992.
[6] J. Gama et al. A Survey on Concept Drift Adaptation. ACM Computing Surveys, 46(4), 2014.
W3 & Q3: Only a linear prediction model.
Thanks for raising this question. The current formulation is intentionally scoped to a channel-independent linear forecaster. Replacing this backbone with a more expressive model is not a plug-in change, because the lag summaries and closed-form solve are derived specifically for the linear forecasting problem. Our claim concerns communication, not higher accuracy than nonlinear iterative methods.
(1) The closed-form solve is specific to the linear model. FedTinyTS is an analytic FL method, so the model is fitted in closed form, not by gradient descent, and a closed-form solve is derived for one model. Changing the backbone means deriving a different solve (scope stated at the end of Section 2 and in the Conclusion).
(2) The closed-form baselines share this restriction. The DLSA [2] and FedRidge [3] baselines in our experiments are instantiated on the same linear forecasting design. FedRidge performs exact single-round aggregation of ridge-regression sufficient statistics, whereas DLSA more generally combines local quadratic approximations. Neither provides a direct nonlinear replacement for the specific FedTinyTS lag-summary solve evaluated here.
(3) What we claim. A competitive linear forecaster [1] can be fitted in one round with an upload of numbers. Fixing the backbone separates the communication comparison from backbone capacity.
(4) A route to nonlinear models. Analytic FL on a fixed or layer-wise feature map (AFL [4] and DeepAFL [5], Section 2) puts the closed-form solve on top of the features. Cross-channel lag summaries are future work (Conclusion).
(5) Revision. We revised the Conclusion (in red) to state that the results cover this backbone only and that analytic learning on a feature map is one route to nonlinear models.
[1] A. Zeng, M. Chen, L. Zhang, Q. Xu. Are Transformers Effective for Time Series Forecasting? AAAI, 2023.
[2] X. Zhu, F. Li, H. Wang. Least-Square Approximation for a Distributed System. JCGS, 30(4), 2021.
[3] Z. Alsulaimawi. One-Shot Federated Ridge Regression. arXiv:2601.08216, 2026.
[4] R. He et al. AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models. CVPR, 2025.
[5] J. Tang et al. DeepAFL: Deep Analytic Federated Learning. ICLR, 2026.
Thanks for raising this question. The MAE gap primarily reflects the mismatch in training objectives rather than lag compression, and under the same training loss FedTinyTS has the lowest MAE.
(1) Global MAE under the original training losses. The analytic methods minimize squared error, so they target the conditional mean, while the gradient baselines in the MAE column were trained with an MAE loss, which targets the median. DLSA [1] and FedRidge [2], which have no robust weighting, show the same gap to FedAvg. Our Huber weighting lowers MAE below FedRidge in 19 of 20 settings, but only slightly, since with cH=1.345 most windows stay in the quadratic regime.
Table R1. Global MAE, mean over horizons (Table E5), increase over FedAvg in parentheses:
Finding. All three analytic methods trail FedAvg by a similar margin, so the gap belongs to the squared-error fit, not to compression.
(2) Global MAE with all methods trained on MSE. We trained the gradient baselines with MSE, the same loss as ours, and scored them on MAE (best round per seed, 3 seeds). MSE is minimized by the mean and MAE by the median [3], so an MAE column favors models trained for the median. Training everyone with MSE removes that advantage.
Table R2. Global MAE, mean over horizons, all methods trained with MSE (change of FedTinyTS vs FedAvg):
Finding. Under the same training loss, FedTinyTS has the lowest MAE on all five datasets. On SolarEnergy the gap to FedAvg goes from +25.2% to −0.6%.
(3) Personalized MAE with LocalOnly trained on MSE. LocalOnly is gradient-trained too, and its MAE in Table E6 also comes from an MAE-trained run. We scored its MSE-trained client models on MAE in the same way (3 seeds).
Table R3. Personalized MAE, mean over horizons (change of FedTinyTS vs LocalOnly):
Finding. Under the same training loss, personalized FedTinyTS has lower MAE than LocalOnly in all 20 dataset-horizon settings. LocalOnly is scored on its saved best checkpoint, which the framework writes one round after the best evaluation. On ETH its MSE there is 0.3599 against the recorded 0.3557, and on the other four datasets the two agree to four decimals.
(4) Revision. We added (2) and (3) to Appendix E.3 (Table E10, in red).
[1] X. Zhu, F. Li, H. Wang. Least-Square Approximation for a Distributed System. JCGS, 30(4), 2021.
[2] Z. Alsulaimawi. One-Shot Federated Ridge Regression. arXiv:2601.08216, 2026.
[3] H. Hewamalage, K. Ackermann, C. Bergmeir. Forecast Evaluation for Data Scientists: Common Pitfalls and Best Practices. DMKD, 37, 2023.