- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes ROAR, a visual autoregressive framework for time series forecasting. It transforms 1D time series data into 2D visual representations and performs autoregressive prediction over randomly ordered visual tokens. ROAR has a dual-branch training strategy combining teacher forcing and free running to mitigate exposure bias and error accumulation. Experiments demonstrate competitive forecasting performance, particularly for long prediction horizons.
Critical strengths
S1. An alternative approach to autoregressive modeling.
- ROAR explores random-order autoregressive generation over visual tokens while preserving their positional identities, providing an alternative way to conventional autoregressive forecasting.
S2. Comprehensive empirical evaluation.
- The paper provides a comprehensive evaluation across multiple SOTA benchmarks, including extended-horizon experiments, component ablations, and robustness analyses. The results support the effectiveness of the proposed components under the evaluated settings.
Critical weaknesses
W1. Limited distinction from prior visual time series modeling approaches.
- Prior works, including TimesNet, VisionTS, and AURORA (ICLR 2026), have explored 2D representations or visual modeling for time series forecasting. ROAR's main contribution is therefore its random-order autoregressive modeling rather than the 1D-to-2D transformation itself. Although the ablation results show that random-order training improves performance over fixed-order training, the paper does not establish whether this benefit specifically depends on the visual representation.
W2. Insufficient analysis of training and inference consistency.
- Random-order teacher forcing may use temporally later ground-truth tokens to predict earlier ones, creating a potential mismatch with fixed-order inference. Moreover, free-running training covers only within-window generation, leaving its effectiveness in mitigating error accumulation across recursive forecasting windows unclear.
W3. Limited robustness analysis of period-based visual representations.
- ROAR constructs 2D representations using dataset-specific periodicities, but does not systematically evaluate sensitivity to period selection or robustness under dynamic patterns. This leaves the generalizability of the proposed representation unclear, particularly when a single fixed period can't adequately capture the temporal structure.
Questions for authors
Q1. About Random-order autoregression.
- Would applying the same random-order autoregressive mechanism directly to 1D temporal tokens yield comparable improvements? What specific advantage does the 2D visual representation provide?
Q2. Periodicity and generalization
- How sensitive is ROAR to the selected periodicity, particularly under multiple, changing, or weak periodic patterns? What about datasets with non-stationary properties?
6 comments
Response to Reviewer fmZk (Part 2)
A2. Temporally later tokens during training provide richer contextual supervision than standard left-to-right autoregression, thereby stabilizing optimization and enabling ROAR to learn more comprehensive temporal dependencies. At inference, no future tokens are used as conditions for autoregressive generation. Instead, inference strictly follows the standard order, which ensures coherent and stable predictions. To verify this empirically, we evaluated autoregressive inference under random orders (Table R2). Averaged over three seeds, random-order inference consistently underperforms standard-order inference.
Table R2. MSE under standard-order and random-order inference at the longest horizon and averaged over the four horizons (three seeds).
| Horizon | ETTh2 standard | ETTh2 random | Exchange standard | Exchange random |
|---|---|---|---|---|
| 720 | 0.413 | 0.419 | 0.702 | 0.781 |
| 1080 | 0.465 | 0.473 | 1.086 | 1.184 |
| 1440 | 0.514 | 0.524 | 2.163 | 2.216 |
| 1800 | 0.549 | 0.555 | — | — |
| 2160 | 0.580 | 0.583 | — | — |
| Avg. (96–720) | 0.362 | 0.367 | 0.328 | 0.346 |
Regarding free running, it acts within one forecasting window and reduces exposure bias, so every forecast that is fed back to later windows is more reliable. We further examined the ablation at the longest horizon H=720, which requires eight recursive windows (Table R3). Removing free running clearly degrades the forecast, which shows that its gain is retained across recursive windows.
Table R3. MSE / MAE at H=720 with and without free running (mean ± standard deviation over three seeds).
| Metric | ETTm1 | ETTm2 | Wind | |
|---|---|---|---|---|
| ROAR | MSE | 0.414 ± 0.003 | 0.375 ± 0.003 | 1.340 ± 0.006 |
| ROAR | MAE | 0.424 ± 0.001 | 0.394 ± 0.003 | 0.862 ± 0.003 |
| Without free running | MSE | 0.549 ± 0.079 | 0.424 ± 0.005 | 1.420 ± 0.004 |
| Without free running | MAE | 0.491 ± 0.033 | 0.429 ± 0.004 | 0.898 ± 0.002 |
A3. Regarding the sensitivity to period selection, we added a period-sensitivity experiment, as shown in Figure R1(https://anonymous.4open.science/r/ROAR-6702/rebuttal/fig1.jpg). On benchmarks with a clear and stable temporal structure, deviating from the dominant period changes the phase alignment of the visual representation, which leads to a performance degradation. A smaller period splits one complete cycle across several columns, which weakens the ability of each column to express the full intra-period pattern. A larger period packs several cycles into one column, which introduces redundant information and leaves fewer repeated periods across columns.
Regarding datasets without a clear temporal structure and with non-stationary properties, ROAR remains effective and generalizes well. Exchange is a strongly non-stationary benchmark: its level drifts over time and it shows no stable periodicity, as shown in Figure R2(https://anonymous.4open.science/r/ROAR-6702/rebuttal/fig2.jpg). On Exchange, ROAR achieves the best MSE and MAE among all ten methods (Table R4). This indicates that ROAR is not limited to data with a stable periodic structure and generalizes to non-stationary data.
Table R4. Results on Exchange, averaged over the four horizons.
| Method | MSE | MAE |
|---|---|---|
| ROAR | 0.328 | 0.392 |
| TimeTK | 0.361 | 0.410 |
| VisionTS | 0.377 | 0.420 |
| PatchTST | 0.411 | 0.434 |
| iTransformer | 0.422 | 0.442 |
| AutoHFormer | 0.434 | 0.447 |
| TimeLLM | 0.441 | 0.459 |
| TimeMixer | 0.492 | 0.486 |
| Timer-XL | 0.851 | 0.611 |
| TimesNet | 0.993 | 0.659 |
In summary, the period-sensitivity results are incorporated into Appendix K (Figure 14 and Table 11, Lines 1285–1328) of the revised manuscript.
Thank you for the clarifications and additional experiments. Table R1 and Table R3 address my earlier concerns. But several points still to be clarified.
-
The Consistency of reported results.
- The standard-order ETTh2 results in Table R2 differ a lot from those in the original Table 7. Were the same checkpoints, and evaluation settings used?
- Please also add the std in Table R2.
-
Scope of the periodicity analysis.
- My concern is not only about sensitivity to the chosen folding period, but also whether a single fixed period remains suitable when the temporal structure changes across different segments of the same series. Varying fixed periods and reporting aggregate results on Exchange data as a whole do not directly address this issue. Is there evidence that ROAR remains effective across such changes under a fixed configuration?
Response to Reviewer fmZk (Part 1)
Many thanks to Reviewer fmZk. Regarding the weaknesses and questions, we respectfully provide point-by-point clarifications below:
A1. TimesNet transforms a time series into 2D tensors to capture its periodic characteristics. VisionTS introduces a visual representation of time series and couples it with a heavy pretrained vision backbone to enhance representation learning. AURORA distills informative features from the endogenous images of a series to improve forecasting accuracy. ROAR differs from these methods: through the additional spatial property introduced by the visual representation, it extends standard autoregression from the original time axis to a more flexible random-order autoregressive modeling paradigm, which effectively improves forecasting performance and robustness.
To evaluate the effectiveness of random-order autoregression more comprehensively, we added an ablation. Specifically, we added a pair of variants, standard autoregression on 1D temporal tokens and random-order autoregression on 1D temporal tokens, verifying whether the performance gain of ROAR depends only on the visual representation transformation in a more isolated manner. As shown in Table R1, random-order autoregression on 1D temporal tokens outperforms standard autoregression on 1D temporal tokens. This indicates that the gain brought by ROAR does not rely solely on the visual representation transformation. In addition, regarding the advantage provided by the 2D visual tokens, random-order autoregression on 2D visual tokens achieves the best performance among all variants. This is consistent with the reflection and analysis in our introduction: compared with 1D temporal tokens, the additional 2D spatial property introduced by the visual representation provides the basis for more flexible autoregressive modeling and gives ROAR a more comprehensive ability to learn from context, which improves the downstream forecasting performance.
Table R1. Average MSE over the four horizons with standard and random-order autoregression on 1D temporal tokens and on 2D visual tokens (three seeds).
In summary, the ablation is incorporated into Appendix J (Table 10, Lines 1266–1282) of the revised manuscript.