- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes FAPA, a dual-branch framework for time-series forecasting that separates periodic components from irregular residuals. The periodic branch predicts the periodic component without window normalization and introduces an amplitude shaping module (AmpShape). Harmonic Period Alignment (HPA) is further used to construct training targets at the input-window frequencies. Experiments across eight forecasting backbones and five datasets report an overall MSE reduction of 10.7%. The results are encouraging, although the methodological novelty and generality of the improvements need further justification.
Critical strengths
-
The paper addresses a meaningful problem in time-series forecasting. Separating periodic components from irregular residuals is reasonable, especially when their amplitude scales differ significantly.
-
I find the HPA design interesting. Using input-window periods to construct the future periodic target avoids the frequency-grid mismatch caused by different input and prediction lengths.
-
The empirical results are fairly convincing. FAPA improves the five-dataset average across all eight backbones, and the synthetic experiments provide useful evidence about the role of amplitude imbalance.
Critical weaknesses
-
Novelty is somewhat limited. Frequency decomposition and separate periodic prediction have already been explored, particularly in FAN. HPA mainly builds on harmonic projection, and I am not fully convinced that the overall framework represents a substantial methodological advance.
-
The improvements vary considerably across datasets. Most gains come from ECL and Traffic, while ETTm2 shows almost no improvement.
-
The ablation study is somewhat narrow. It only uses PatchTST on ETTm1 and ETTm2. I would like to see whether the same conclusions hold on datasets with larger improvements.
-
The comparison with FITS may be affected by the fixed input length of 96. Stronger comparisons with FAN and simpler decomposition-based alternatives would also be helpful.
Questions for authors
-
What is the main methodological difference between FAPA and FAN? Could the authors provide a direct comparison under the same forecasting backbones and experimental settings?
-
HPA uses least-squares projection onto sinusoidal bases. What makes this formulation particularly advantageous over simpler harmonic regression or frequency-alignment approaches?
-
Could the authors extend the ablation study to ECL and Traffic? I would like to understand whether AmpShape and HPA contribute equally on these datasets.
-
How sensitive is FAPA to the input length and the number of selected frequencies? Would the improvements remain stable when the dominant periodic patterns change over time?
7 comments
Response 2
Thank you for this question. HPA is fundamentally harmonic regression; its advantage lies in how the supervision target is constructed. It fits the future periodic component directly at the input-selected frequencies, preserving periodic consistency between the input and target while avoiding approximation errors from mapping those frequencies to the nearest FFT bins. The projection is used only during training and adds no inference overhead. We will clarify how HPA uses harmonic regression to construct consistent supervision targets.
We held the input-selected periods fixed and changed only the target reconstruction method:
Table 2. Harmonic projection vs. nearest-bin reconstruction.
| H | PatchTST Nearest bin | PatchTST Full | DLinear Nearest bin | DLinear Full | iTransformer Nearest bin | iTransformer Full |
|---|---|---|---|---|---|---|
| 96 | 0.318 | 0.318 | 0.327 | 0.327 | 0.342 | 0.342 |
| 192 | 0.359 | 0.359 | 0.365 | 0.365 | 0.381 | 0.381 |
| 336 | 0.396 | 0.388 | 0.429 | 0.397 | 0.425 | 0.413 |
| 720 | 0.448 | 0.450 | 0.487 | 0.460 | 0.497 | 0.480 |
The table reports MSE averaged over three seeds on ETTm1 with input length 96; lower is better.
At H = 96/192, the input-selected frequencies exactly match FFT-bin frequencies of the target window, so the two reconstruction methods are theoretically equivalent without regularization and yield identical reported results. At H = 336/720, some input-selected frequencies fall between target bins, and HPA avoids the errors introduced by nearest-bin substitution. The forecasting benefit still depends on the energy and predictability of the corresponding periodic components; improvements do not occur in every setting.
Response 3
Thank you for this suggestion. We extended the PatchTST ablation study to ECL and Traffic. Given the time and computational constraints during rebuttal, we focused on representative datasets and forecasting horizons.
Table 3. ECL and Traffic ablations.
| Dataset | Horizon | Full | −HPA | −AmpShape |
|---|---|---|---|---|
| ECL | 96 | 0.182 | 0.182 | 0.188 |
| ECL | 720 | 0.234 | 0.235 | 0.240 |
| Traffic | 96 | 0.541 | 0.541 | 0.547 |
| Traffic | 720 | 0.575 | 0.575 | 0.580 |
HPA has a small effect in these settings. This is consistent with the paper’s periodicity analysis: the position consistency values are 0.90 for ECL and 0.98 for Traffic, indicating stable period selection. Their dominant daily period is also 24 time steps, and all forecasting horizons are multiples of 24, so the corresponding frequency aligns with the target window’s frequency grid. AmpShape further improves forecasting in these settings. We will include these additional ablations and discuss how each component contributes across datasets.
Response 1
Thank you for this suggestion. We added a direct comparison using the same backbones and experimental protocol, with FAN’s K set to the dataset-specific values reported in its paper. Across five datasets and four horizons, FAPA achieves lower reported MSE in all 20 settings for each of PatchTST and iTransformer, with relative reductions in average MSE of approximately 11.31% and 10.19%, respectively.
FAPA and FAN differ in the purpose of the periodic branch and how its predictions are supervised and refined. FAN uses frequency decomposition for reversible normalization: it removes dominant nonstationary components to improve residual stationarity, predicts their future values, and adds them back to the backbone forecast. Across the compared datasets, FAN uses the K values reported in its paper (K = 2–30), with DC included among the selection candidates. FAPA instead dedicates a lightweight branch to forecasting a compact set of dominant periodic components, using K = 1–2 non-DC frequencies while retaining the mean in the residual. This design separates regular periodic structure from the remaining dynamics, allowing the periodic predictor and backbone to model components with different structures and amplitude scales. FAPA further provides consistent supervision for this periodic forecast through Harmonic Period Alignment (HPA). Whereas FAN independently selects the future window’s Top-K frequencies and reconstructs its target from FFT bins, HPA constructs the future periodic target at the input-selected frequencies through harmonic projection. The input and target therefore share the same frequency basis, even when these frequencies fall between the target window’s FFT bins. FAPA applies auxiliary supervision specifically to this aligned periodic target, while the residual branch learns through the final forecasting loss; FAN’s official implementation supervises both components separately. Finally, AmpShape provides explicit frequency-wise, channel-wise amplitude refinement of the MLP prediction, a mechanism absent from FAN. FAPA thus combines focused periodic modeling, aligned supervision, and explicit spectral refinement. We will clarify these differences and include the direct comparison in the revised manuscript.
Table 1. FAN comparison.