- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper reformulates long-term time-series forecasting as Patch-to-Horizon Contribution Learning (PHCL). Its instantiation, Patch-Horizon Lifting (PHL), constructs raw, fixed-wavelet, and learnable-lifting patch candidates; uses horizon queries and a recency prior to route a sparse subset of candidates; maps each selected patch to a signed scalar effect; and fuses their weighted sum with a persistence anchor. Experiments on eight standard benchmarks report the best average MSE among the listed methods, while routing diagnostics and visualizations are presented as evidence that different horizons use different historical patches.
Critical strengths
-
The modeling motivation is intuitive. Different future steps can depend on different parts and resolutions of the history. Combining multi-resolution candidates with horizon-conditioned sparse routing is a reasonable inductive bias for this setting.
-
The reported forecasting accuracy is strong. PHL improves average MSE on all eight listed datasets, including high-dimensional Electricity, Traffic, and Solar. The gains on several ETT datasets are substantial relative to the reported recent baselines.
-
The paper makes a useful attempt to inspect internal routing behavior. The router ablations, sparsity analysis, and patch-resolution maps go beyond reporting only aggregate forecasting errors.
Critical weaknesses
-
The learned quantities are not established as predictive contributions. The softmax weights are routing weights, whereas the output terms are , with jointly learned by patch-, position-, resolution-, and horizon-specific experts. Multiple router/expert parameterizations can produce the same forecast but very different maps. The final output is further altered by the anchor and gate. Without perturbation, deletion/insertion, retraining, or synthetic ground-truth tests, the maps are not shown to be faithful explanations of model predictions. Calling them the patches "responsible" for a forecast is therefore stronger than the evidence supports.
-
The central horizon-specific claim is not isolated by the ablations. The uniform, prior-only, and dense-router variants test different routing and sparsity choices, but there is no parameter-matched horizon-agnostic router or shared-query control. Likewise, the paper does not compare against an otherwise identical model that uses the same multi-resolution candidates, experts, and anchor but a shared historical representation. The results establish that the complete PHL architecture works, not that PHCL is a distinct or necessary forecasting paradigm.
-
Extra output-head capacity is a major confounder. Equation (7) assigns separate weights and biases to every horizon, resolution, and patch position. This is already a direct horizon-specific linear mapping from the full look-back window, in addition to adaptive routing and anchor fusion. The paper does not compare against a dense linear head or a static mixture with the same position-specific parameters, so the gain cannot be attributed specifically to contribution learning.
-
The scalability cost is omitted despite an unfavorable dependence on horizon and channel count. With the stated , patch length 16, stride 8, and a two-level decomposition, there are 64 patches and 7 resolution components. At , Equation (7) alone implies about 5.16M weights, while router scores scale as ; for Traffic this is about 278M scores per sample before top- selection. No parameter count, FLOPs, memory, training time, or inference latency is reported.
-
The empirical protocol is insufficiently specified for the strength of the accuracy claim. The appendix gives wavelet choices for only ETTh1, ETTm1, and Weather, and omits key optimization details, tuning ranges, seeds, and uncertainty. It is also unclear whether all baseline results were rerun with the same input length, data pipeline, tuning budget, and number of trials. Without variance estimates, the reliability of smaller differences cannot be assessed.
-
Several diagnostics partly reflect mechanisms imposed by construction. A top- contribution mass of 1.00 is expected after masking and renormalization, and high recent-patch mass is encouraged explicitly by Equation (5). Comparisons across and also appear to involve separately trained forecast-length settings and do not directly quantify how evidence changes across output steps within one model. These observations do not independently validate horizon-specific predictive responsibility.
-
There are unresolved reporting and specification issues. The appendix states that PHL has the best average MSE on seven of eight datasets, whereas Tables 1 and A2 show it as best on all eight. The ordering and meaning of the normalized component index in the hand-designed prior are not defined clearly, even though raw, fixed-wavelet, and learnable-lifting components do not naturally form one ordinal scale. Complete dataset-specific configurations are also missing.
Questions for authors
-
Contribution faithfulness: How do the reported maps change under deletion or replacement of high-contribution patches, and do they outperform attention weights, gradients, or occlusion scores in predicting the resulting output change? Can this be tested on synthetic data with known horizon-dependent dependencies?
-
Central-claim control: Can the authors compare full PHL with a capacity-matched shared-query or horizon-agnostic router, and with a conventional decoder using exactly the same multi-resolution encoder, patch experts, anchor, and parameter budget?
-
Capacity attribution: How much of the improvement remains if is shared across patch positions or replaced by an equally sized dense linear forecasting head? Please report component-wise parameter counts.
-
Efficiency: What are the measured peak memory, training throughput, and inference latency on Electricity and Traffic at , including the cost of constructing and scoring all candidates before top-?
-
Reproducibility: Were all baselines rerun under exactly the same input length and tuning budget? Please provide complete configurations for every dataset, results over multiple seeds, and uncertainty or paired significance analysis.
-
Horizon specificity: Can the authors quantify within-model differences among and the resulting selected patches across output steps, rather than mainly comparing models trained for different forecast lengths?