- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes KOR for representing high-frequency components in multivariate time series forecasting and integrates it into the KFM framework through soft-gated frequency decomposition and spectral fusion. Experiments on nine public datasets evaluate forecasting performance across multiple backbones, alongside module ablations, replacement experiments, robustness analysis, and computational comparisons.
Critical strengths
- The experiments cover nine datasets and six forecasting backbones, providing broad evidence of the framework’s effectiveness.
- Ablation, module-replacement, and robustness studies examine the contributions of KOR and the other KFM components.
Critical weaknesses
- The framework combines oscillator dynamics, frozen random projections, frequency decomposition, and spectral fusion. The specific contribution of Kuramoto dynamics relative to generic fixed random-feature representations is not fully isolated.
- The dynamical interpretation is supported by theoretical analysis, but the connection between the proposed phase dynamics and the observed forecasting improvements could be established more directly.
Questions for authors
See the above weakness.
2 comments
Response to Reviewer YEqA (Question 2)
Q2. Direct link between phase dynamics and forecasting
In KOR, the high-frequency input first becomes the external oscillator drive . The local Adler analysis shows how changes an oscillator's effective frequency mismatch relative to the coupling field. Under locally quasi-stationary conditions, the relation between mismatch and coupling strength determines local phase locking or slipping. KOR then forms its forecasting representation from the driven–free phase difference, . This gives a specific path from input drive through phase response to forecast. We therefore measured changes in the phase readout used by the model alongside changes in forecast error.
On the same Weather test batch, we changed only the projected oscillator drive while keeping the trained model, future targets, and other forecasting branches fixed. Appendix I.1, Table 17 provides the full intervention results. The paired measurements are summarized below. Relative drive change is , total energy change is relative to the original drive, and is the mean relative change in the driven–free phase readout.
| Drive intervention | Relative drive change | Total energy change | Phase-readout change | MSE (change) |
|---|---|---|---|---|
| Original drive | 0.0000 | 0.00% | 0.000 | 0.164 (—) |
| Prominent high-frequency attenuation | 0.0946 | −10.47% | 0.232 | 0.179 (+9.15%) |
| Matched weak high-frequency attenuation | 0.0946 | −2.68% | 0.083 | 0.167 (+1.83%) |
| Matched random high-frequency attenuation | 0.0946 | −6.54% | 0.137 | 0.171 (+4.27%) |
| Prominent/weak high-frequency energy swap | 0.6993 | 0.00% | 0.187 | 0.182 (+10.98%) |
| Spectral inversion (bins 1 to 13) | 1.2785 | 0.00% | 0.244 | 0.180 (+9.76%) |
| Gaussian noise, 20 dB | 0.1000 | +1.02% | 0.032 | 0.166 (+1.22%) |
| Gaussian noise, 10 dB | 0.3162 | +10.07% | 0.048 | 0.167 (+1.83%) |
At the same relative drive change of 0.0946, attenuating prominent high-frequency components changes the phase readout by 0.232 and increases MSE by 9.15%. Attenuating weak components yields 0.083 and 1.83%, while random high-frequency attenuation yields 0.137 and 4.27%. Comparably sized 20 dB Gaussian noise yields 0.032 and 1.22%. Because the intervention enters only through the KOR drive and the other branches remain fixed, its effect on the forecast passes through KOR's phase readout. In this batch, stronger forecast sensitivity to the selected prominent drive components accompanies a larger phase-readout response. The interventions match relative drive-change magnitude, but remove different amounts of energy, so this comparison does not isolate phase organization as the sole cause of the error differences.
The coupling mechanism has complementary phase-level evidence. On the same active ETTh1 oscillator edges, the driven locked-edge fraction is 16.10% for full KOR and 7.79% when both coupling strengths are zero, while MSE is 0.432 and 0.441, respectively. Coupling thus changes local phase organization alongside forecasting accuracy. These observations support the proposed local phase mechanism without implying global synchronization or establishing locking as the sole source of the forecasting gain.
Response to Reviewer YEqA (Question 1)
Q1. Contribution of Kuramoto dynamics beyond fixed random features
The oscillator dynamics, frozen random projections, frequency decomposition, and spectral fusion named in the question all belong to KFM but play different roles. KOR is the core contribution that adapts Kuramoto dynamics to time-series forecasting. It maps high-frequency input to oscillator excitation, evolves within-channel and across-channel coupled phases, and reads out the driven–free phase difference. The frozen random projections are internal to KOR and serve only to map the input to oscillator excitation and align the phase-difference readout with the output feature dimension. The soft gate in Sec. 3.1 routes input between frequency branches, while the spectral fusion in Sec. 3.3 supplies residual spectral information. The main-text ablation in Table 5 shows the largest overall degradation when KOR is removed. On ETTh1, removing KOR raises MSE by 3.47% relative to the full model, compared with 1.16% for removing soft gating and 0.23% for removing spectral fusion. On ETTm1, removing KOR raises MSE by 6.25%, removing spectral fusion raises it by 2.60%, and removing soft gating slightly lowers it by 0.26%. These ablations distinguish the contributions of the three modules within KFM and identify KOR as the primary contributor to forecasting accuracy.
To test whether fixed random features can replace KOR, we added a stateless Fixed Random Features control to the Appendix I.3 module comparison. It retains the high-frequency input, frozen random projections, output feature dimension, spectral fusion, and forecasting head, while replacing iterative oscillator phase evolution with fixed random nonlinear features. We also compare a double-zero-coupling KOR control. It retains the input drive, independent oscillator phase evolution, and driven–free phase-difference readout, while removing inter-oscillator coupling. Each entry below reports MSE / MAE.
Full KOR has lower MSE and MAE than fixed random features on all six datasets. Relative to that control, it reduces MSE by 4.21% on ETTh1 and 6.53% on Electricity. Full KOR also outperforms double-zero-coupling KOR on both metrics across all six datasets. These results show that frozen random features alone do not explain KOR's forecasting gains and that inter-oscillator coupled phase evolution provides an additional contribution.