- Rating
- 3(−1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This work proposes a backbone agnostic multi‑scale time series forecasting framework separating native scale prediction and prediction‑space fusion. It develops Safe linear and RC‑ANSF fusion modules and adopts a two stage training pipeline. Evaluations across three backbones, eight datasets and four horizons verify consistent performance gains from this reusable multi‑scale design.
Critical strengths
- It decouples native‑scale forecasting and fusion, compatible with diverse existing backbones, showing good generalizability for multi‑scale forecasting research.
- It provides bounded risk controlled fusion mechanisms and structural theoretical bounds, constraining harmful cross scale corrections.
Critical weaknesses
- Risk controlled bounds only guarantee parameter space constraints rather than test‑set error improvement; performance gains are task dependent without universal superiority.
- It lacks real world case studies beyond standard public multivariate forecasting benchmarks.
Questions for authors
- Section 3.4 states that "risk control refers to these structural restrictions together with the empirical excess-loss penalty below, rather than a guarantee of non-increasing test error". Is this risk control only a constraint in parameter space, and does it not provide a guarantee of test error reduction in a statistical sense?
- In the experiments, the Scaleformer comparison only reuses the official coarse-to-fine procedure without targeted tuning for the three types of backbones. Is it possible that the actual performance of this comparison method is underestimated?
- Existing multi-scale models such as N-HiTS and TimeMixer have already realized cross-scale fusion. What is the specific core innovation difference of the design in this paper that decouples native prediction and fusion compared with similar methods?
- The discussion section mentions that "the evidence supports task-dependent control of cross-scale corrections, not unconditional improvements from tighter constraints". What specific data characteristics or scenarios will tighter constraints lead to performance degradation?
- Proposition 2 in Appendix A shows that the lower bound of the base model weight is 0 when \alpha=1. Does the fusion mechanism have the potential risk of completely discarding the fine-scale base prediction at this time?
- In the ablation study, "No gate" removes both the participation gate and the candidate-quality supervision at the same time, which cannot verify the role of the gating network alone. Why is a control experiment that only removes the supervision term not designed?
- Safe-linear has already realized deterministic alignment and gated fusion. On this basis, the bounded adaptive residual added by RC-ANSF brings limited gains. Where does the necessity of this module lie?
- The trust radius sensitivity experiment shows completely opposite change trends on the ETTh2 and Traffic datasets. What is the reason for the sequence characteristics behind this difference?
10 comments
Part2 for W2
The all eight main benchmarks we used in our paper contain real-world measurements, including transformer temperatures and loads, weather, electricity usage, road occupancy, and solar output. We extend this offline evaluation beyond multivariate benchmarks to all 414 M4 Hourly univariate series and 30,490 M5 item–store sales series with covariates. M5 forecasts 28 days of sales using iTransformer with historical sales, prices, calendar/event features, and SNAP indicators.
| Task and backbone | Metric | RC-ANSF (Ours) | Safe-linear | Base |
|---|---|---|---|---|
| M4 Hourly / DLinear | MASE | 1.208 | 1.243 | 1.243 |
| M4 Hourly / TimeMixer-Core | MASE | 1.359 | 1.385 | 1.529 |
| M5 / iTransformer | WRMSSE | 0.923 | 0.926 | 0.928 |
The eight main benchmarks cover diverse real-world forecasting domains, supporting the broad applicability of our framework. The supplementary M4 results also demonstrate strong performance on univariate forecasting. Gains on M5 are limited, suggesting less additional benefit in settings with substantial covariate-modeling demands. This is consistent with our design: the fusion framework introduces no dedicated module for modeling relationships between variables, facilitating adaptation to different backbone predictors.
Part3 for Q2
Regarding your concern that insufficient tuning may underestimate Scaleformer's performance, we clarify that the Scaleformer results in our paper already incorporate task-specific learning-rate tuning. For each backbone, dataset, and forecast horizon, we trained the adaptation at , , and times the inherited learning rate, with all scale-specific backbones trainable. We selected the learning rate with the lowest validation MSE within this grid for each of the 96 settings and used that setting's selected rate in the subsequent repeated experiments reported in the paper.
The table illustrates why learning-rate search matters for a fair Scaleformer comparison. Entries are test MSE averaged over eight datasets and four horizons for each backbone; Val.-selected uses the best learning rate selected separately for each setting by validation MSE.
| Backbone | Val.-selected | |||
|---|---|---|---|---|
| DLinear | 0.640 | 0.454 | 0.341 | 0.339 |
| iTransformer | 0.390 | 0.391 | 0.409 | 0.354 |
| TimeMixer-Core | 0.336 | 0.319 | 0.318 | 0.315 |
| Overall | 0.456 | 0.388 | 0.356 | 0.336 |
Without learning-rate search, Scaleformer can perform substantially worse: DLinear's average MSE varies from 0.341 to 0.640 across the tested fixed learning-rate multipliers. Selecting by validation MSE lowers overall test MSE from 0.456 at the inherited rate to 0.336, a 26.21% reduction. Our paper uses the best validation-selected learning rate within the search grid for every setting in the subsequent repeated experiments. Thus, the reported Scaleformer performance is not underestimated through omission of learning-rate tuning.
Part1 for W1 and Q1
Thank you for your questions.
The risk control acts directly in prediction space. It bounds the alignment correction and the total coarse-scale contribution to the fused forecast, independently of projector parameter norms. Describing it as only a parameter-space constraint therefore overlooks the prediction-space guarantees. As explicitly stated in Section 3.4, these structural guarantees do not constitute a statistical guarantee of reduced test error. Their empirical effectiveness is supported by the broad improvements below.
Applicability across datasets and backbones. The same fusion framework works with linear, attention-based, and MLP-based predictors across all eight benchmarks. Relative to each single-scale backbone (Vanilla), its four-horizon average MSE is lower on 8/8 datasets for DLinear, 8/8 for iTransformer, and 6/8 for TimeMixer-Core at the precision reported in the main table. Averaged across backbones, RC-ANSF improves MSE on all eight datasets. Across the 96 evaluated settings, the macro MSE reductions for the three backbones are 14.6%, 5.6%, and 1.4%, respectively. These results demonstrate consistent aggregate gains across diverse forecasting domains and all three predictor families, providing direct empirical support for the broad applicability of RC-ANSF.