- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper argues that historical input formulation is an important yet underexplored part of time-series forecasting. It considers two dimensions of the input: temporal structure and temporal extent. It proposes a training-data-based procedure for selecting those configurations using a unified criterion for expected multi-step forecasting risk. Experiments on public benchmarks show that the configured inputs improve a scalar autoregressive forecaster over commonly used fixed-input configurations and that configuring the temporal extent can also benefit several other state-of-the-art forecasting baselines.
Critical strengths
-
The paper highlights an important but under-explored aspect of time-series forecasting: how historical inputs are formulated. It treats temporal structure and lookback length as task-dependent choices, rather than fixed conventions. Controlled comparisons show that configuring these inputs improves the performance of a fixed scalar autoregressive forecaster. In a separate benchmark comparison, this forecaster is competitive with several recent forecasting baselines. Together, these results motivate further attention to input formulation as a complement to predictor design.
-
The paper presents a well-structured and intuitive training-only criterion for selecting historical-input configurations. It combines reconstructed multi-step forecasting error estimated using a scalar linear autoregressive reference forecaster, coefficient-estimation uncertainty, and persistent level variation, without requiring repeated fitting of downstream forecasters. The extensive ablations examine the effects of configuring temporal structure and extent, comparing candidates on different scales, and including individual criterion components. These experiments help clarify the role of each design choice and make the evaluation easier to interpret.
Critical weaknesses
-
The transferability of the full input configuration remains uncertain. The criterion selects structure and extent using a channel-wise scalar autoregressive reference, which may rank temporal structures differently from downstream forecasters. In Table 3, transferring the full configuration substantially worsens DLinear and PatchTST on Weather dataset, even though transferring alone helps both models. The shared-input models also replace channel-wise choices with a majority structure and median extent, making it unclear whether the failure comes from the AR-based criterion or this aggregation rule. Transfer is evaluated on only three datasets and does not include diverse forecasting baselines, such as models explicitly modeling cross-channel dependencies. This limits the evidence for the paper’s broader applicability to multivariate forecasting.
-
Channel-wise selection leaves the role of cross-channel dependencies unresolved. The criterion evaluates each channel separately and does not use predictive relationships between channels when selecting its input configuration. The experiments do not establish how well this procedure works when cross-channel relationships are important to prediction, which may limit its applicability to multivariate forecasting settings.
-
The method relies on a heuristic configuration space, and the added value of jointly selecting the two input dimensions is not fully established. It searches over four conventional temporal representations and a pre-specified lookback grid. The results show that adapting both dimensions is useful, but it is less clear whether they need to be selected as a coupled pair. It does not compare against selecting and independently and then combining them.
-
The selection criterion may depend strongly on the capacity and inductive bias of its scalar AR reference. Evaluated values, such as the reconstructed multi-step error () are estimated using a channel-wise autoregressive reference. Configurations favored by this reference need not be the best inputs for other forecasting models. Without an alternative reference or a more direct analysis of downstream candidate rankings, it is difficult to assess the reliability of the selection criterion.
Questions for authors
Q1. Could you compare joint selection with independently selecting and and then combining the two choices? For example, could be selected with fixed , while is selected with , using the same training-only criterion.
Q2. How sensitive are the selected configurations to the scalar AR reference? Could you evaluate an alternative training-only reference, such as a lightweight rule-based or other forecasting model, or report how the AR-based candidate rankings align with candidate performance under downstream forecasters?
Q3. Could you expand the full transfer experiment in Table 3 to additional datasets and another recent forecasting architecture?
Q4. Could you analyze whether the method’s gains vary with the importance of cross-channel predictive relationships? A comparison across datasets with weaker and stronger cross-channel dependence would help assess the applicability of channel-wise selection.
7 comments
Response to W2 and Q4: The role of cross-channel predictive relationships
Thank you for suggesting that we examine channel-wise historical input formulation under different cross-channel relationships. We agree that a channel-wise criterion may miss predictive information beyond the target’s own history. We therefore compared independent AR with cross-channel-assisted estimation on ETT and PEMS, retaining the same historical input formulations.
For each channel and horizon, is determined from the complete training segment only. The assisted estimator uses training-time lagged second-order statistics from all channels to construct auxiliary correlation estimates for the target, followed by coefficient estimation through the Yule–Walker equations. At prediction time, both methods use only the target channel’s history and fixed AR coefficients.
Both methods use the same data splits, complete test forecast origins, and evaluation metrics. All channels are included, and prediction errors are normalized by each channel’s original-training standard deviation.
Internal standardization during fitting differs: independent AR uses the transformed training mean and standard deviation, whereas the assisted version uses mean 0 and scale 1, omitting internal centering and scaling. Table 2 therefore reports the combined effect of cross-channel-assisted estimation and this standardization choice; its full gains cannot be attributed solely to cross-channel information. Final metric normalization is identical.
Table 2. Mean MSE at fixed historical input formulations. Channels and the four horizons receive equal weight. Internal fitting standardization differs as described above.
| Dataset | Independent AR MSE | Cross-channel-assisted estimation MSE | MSE reduction |
|---|---|---|---|
| ETTh1 | 0.42754 | 0.40931 | 4.26% |
| ETTh2 | 0.34861 | 0.33253 | 4.61% |
| ETTm1 | 0.34429 | 0.34139 | 0.84% |
| ETTm2 | 0.24310 | 0.23615 | 2.86% |
| PEMS08 | 0.38577 | 0.30644 | 20.56% |
| PEMS04 | 0.17159 | 0.15330 | 10.66% |
To examine this confound, we also evaluated an independent AR control with the same formulations and no internal centering or scaling. Relative to this control, assisted estimation reduces four-horizon mean MSE from 0.324054 to 0.306437 on PEMS08 (5.436%) and from 0.156828 to 0.153298 on PEMS04 (2.251%). These reductions are computed as one minus the ratio of the respective four-horizon mean MSEs.
PEMS records traffic flow across a road network, where connectivity, traffic propagation, and shared demand may support cross-channel prediction. ETT contains variables with different physical roles and temporal responses. These contexts offer an interpretation of the different gains, not a direct measurement of cross-channel predictive dependence.
The original formulation procedure is reused. Additional cost arises during training, from constructing cross-channel statistics and estimating coefficients. At prediction time, the input channel count and AR order remain unchanged, giving the same asymptotic forecasting complexity as independent AR with the same formulation.
These results show that channel-wise historical input formulation can be combined with cross-channel-assisted estimation. Gains at fixed formulations do not directly quantify how the benefit of formulation itself varies with cross-channel dependence. Because inference still uses only the target’s history, the estimator does not exploit information available exclusively in other channels at the forecast origin.
We will include these results and estimator details in the revised manuscript, clarifying the distinction between channel-wise input formulation and cross-channel information used during estimation. We thank the reviewer for motivating this analysis, which identifies incorporating cross-channel predictive utility directly into historical input formulation as a concrete direction for extension.
Response to W3 and Q1: Joint formulation versus independent combination
Thank you for suggesting a direct comparison with independently configuring and then combining the two input dimensions. We include this control alongside the single-dimension ablations to distinguish the benefit of adapting both dimensions from the additional value of accounting for their coupling.
All four settings use the same training-only criterion for channel and forecast horizon :
- Structure only: Configure the temporal structure at fixed extent :
and use .
- Extent only: Configure the temporal extent under identity:
and use .
-
Independent combination: Determine both quantities separately as above, then use . Neither dimension is reconfigured after combination.
-
Joint formulation: Configure both dimensions together:
The comparison covers seven datasets and . Each channel–horizon formulation uses the complete training series, without validation or test outcomes. We hold the scalar linear autoregressive forecaster, data splits, candidate families and extents, reconstruction rules and evaluation protocol fixed.
Table 3. MSE / MAE under four historical input formulations, averaged equally over four horizons. Reconstructed errors are normalized by each channel's original-training standard deviation. Channels are equally weighted within tasks; the overall mean equally weights all 28 dataset–horizon tasks.
| Dataset | Structure only | Extent only | Independent combination | Joint formulation |
|---|---|---|---|---|
| ETTh1 | 0.4159 / 0.4214 | 0.4456 / 0.4479 | 0.4337 / 0.4371 | 0.4275 / 0.4322 |
| ETTh2 | 0.3595 / 0.3964 | 0.7684 / 0.5769 | 0.3572 / 0.3980 | 0.3486 / 0.3982 |
| ETTm1 | 0.3606 / 0.3840 | 0.3461 / 0.3783 | 0.3450 / 0.3782 | 0.3443 / 0.3774 |
| ETTm2 | 0.2626 / 0.3166 | 0.3370 / 0.3699 | 0.2447 / 0.3141 | 0.2431 / 0.3140 |
| Weather | 0.2465 / 0.2929 | 0.2118 / 0.2656 | 0.2181 / 0.2680 | 0.2171 / 0.2662 |
| Electricity | 0.1680 / 0.2606 | 0.1644 / 0.2635 | 0.1634 / 0.2600 | 0.1651 / 0.2617 |
| Traffic | 0.4607 / 0.2922 | 0.4486 / 0.3197 | 0.4440 / 0.3069 | 0.4486 / 0.3069 |
| Overall mean | 0.3248 / 0.3377 | 0.3888 / 0.3746 | 0.3152 / 0.3375 | 0.3135 / 0.3367 |
Adapting both dimensions. Relative to structure only and extent only, joint formulation achieves mean task-wise relative MSE reductions of 4.23% and 10.60%, respectively, with 19 wins and 9 losses in each comparison. These ablations support complementary average benefits, but alone do not establish an advantage over independent combination.
Joint versus independent combination. Independent obtains overall MSE / MAE of 0.3152 / 0.3375, versus 0.3135 / 0.3367 for Joint. Joint's mean paired relative MSE reduction is 0.36%, with 18/0/10 wins/ties/losses and a descriptive 95% task-bootstrap interval of [-0.22%, 0.96%]. The means are slightly lower, but the interval crosses zero; these results do not establish a clear joint-formulation advantage or show that joint search is necessary. All reported percentage reductions are computed within each task before equal averaging, not from ratios of overall MSE means.
The methodological motivation is that temporal structure changes both the dependencies presented to the forecaster and error propagation through reconstruction. An extent configured under identity may therefore differ from one preferred under another representation. Joint evaluation accounts for this interaction within the criterion; that motivation alone does not establish superior forecasting.
We agree that the four representation families and finite extent grid are predefined design choices: a compact, interpretable and reproducible implementation, not an exhaustive characterization of historical inputs. We will clarify their rationale and scope, including representation-specific boundary handling.
We thank the reviewer for motivating this distinction. We will report the independent-combination control and single-dimension ablations together, distinguishing adaptation benefits from the additional value of joint formulation. These comparisons are development-stage results.
Response to W1: Full historical input formulation transfer and channel heterogeneity
Thank you for highlighting the uncertainty in full-formulation transfer and the confounding between the reference criterion and the aggregation rule. To investigate this issue, we conducted additional experiments across all four Weather horizons, grouping channels by their training-derived temporal structures and fitting a separate forecaster for each group. This substantially mitigates the degradation for both DLinear and PatchTST.
In the original transfer implementation, channel-specific historical input formulations are reduced to a majority temporal-structure family and a median lookback, which are then shared across channels. This can override channel-specific temporal structures. For example, at longer Weather horizons, precipitation channels originally associated with the identity representation are instead subjected to seasonal differencing. Such reassignment may be unfavorable because inverse differencing can accumulate forecast bias and correlated errors.
To examine whether preserving channel heterogeneity can mitigate the observed degradation, we conducted grouped experiments across all four Weather horizons, H∈96,192,336,720. At each horizon, channels were grouped according to their training-derived temporal structures mc. Each group received a separately trained forecaster with its corresponding preprocessing. All groups used a common lookback of p=1776. We retained the original data splits, training recipe, and original-scale evaluation metrics.
Table 1. Four-horizon mean test MSE for shared and grouped historical input formulations on Weather.
The grouped alternative reduces mean MSE from 0.6563 to 0.2286 for DLinear and from 0.6729 to 0.2722 for PatchTST. These results are consistent with preserving channel heterogeneity being a useful mitigation for the degradation observed under global sharing. However, the grouped procedure also changes temporal extent, parameter sharing, and total model capacity. Its additional cost includes training and maintaining four separate sub-models per task.
The remaining differences across predictors are also informative. Grouped DLinear achieves slightly lower mean MSE than its extent-only identity baseline, whereas grouped PatchTST remains worse than both that baseline and the fixed-input baselines. Thus, grouping substantially mitigates the original degradation but does not establish uniformly beneficial full-formulation transfer.
We agree that the reference criterion may rank temporal structures differently from downstream neural forecasters. At the same time, the remaining PatchTST gap cannot be uniquely attributed to that criterion, because the grouping granularity, shared temporal extent, model capacity, and optimization also affect downstream performance. The present experiment does not fully disentangle these factors.
We will include these results and their additional cost, distinguish channel-specific historical input formulation from its adaptation to shared-input architectures, and qualify our claims about full-formulation transfer. We address the reviewer’s complementary concern about dataset and architecture coverage in our response to Q3.