- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
Traditional time series prediction models use a fixed-length input window for each prediction and cannot explicitly retain information accumulated from previous prediction instances. The paper proposes CoLP to address this limitation. The experiments cover 8 commonly used benchmark datasets and 4 prediction lengths. The paper reports that CoLP achieves 13 best and 2 second-best results in the aggregated results of 16 datasets. This proves the effectiveness of this paradigm.
Critical strengths
-
The problem setting has practical significance. In reality, time series data arrives in a streaming manner, and historical observations may indeed provide useful information for subsequent predictions.
-
CoLP uses predicted position-aligned query tokens to represent the potential state, and then reads the historical state through cross-attention. This design makes the memory units have clear predictive semantics compared to directly passing the hidden states of traditional RNNs.
-
The experiment coverage is relatively comprehensive.
Critical weaknesses
-
If CoLP predicts every time steps, while the baseline still uses a standard sliding window and generates predictions at each time step, the sets of prediction starting points used to compute the test error may differ. This can affect the statistical meaning of the metrics and also the comparability of the results.
-
Numerical differences exist between the main results and ablation experiments, such as weather MSE 0.215 in table 1 and 0.229 in table 2.
Questions for authors
-
Are all models making predictions at exactly the same timestamps? What is the window stride during the test phase? Are MSE and MAE averaged based on the prediction start points or all prediction points?
-
The core claim of the paper is that latent states can continuously accumulate and reuse information across multiple prediction instances. However, the training stage uses a limited context length , while the inference propagation length experiments on page 9 only show . Can the model maintain performance and stability without resetting and during long-term operation?
3 comments
Thank you for your reply, which solved my problem. I will keep my positive score.
Response to Reviewer Y54x
Dear Reviewer Y54x,
Thank you very much for your thoughtful comments and for taking the time to review our manuscript. We are glad that we were able to address and improve upon the points you raised, including the necessary clarifications of our paper.
We hope our work will inspire further research toward practical time-series forecasting.
If you have any further questions, we would be happy to hear them.
Best regards,
Authors
Response to Reviewer Y54x
Dear Reviewer Y54x,
We sincerely appreciate your careful review and thoughtful comments. In what follows, we address your concerns one by one. Note that we only report MSE results in this rebuttal due to the space limit. Please refer to the revised manuscript, as all our responses follow its updated content and numbering.
[Response to W1, Q1] Thank you for raising this important point of clarification. We clarify that CoLP and all baselines follow the same sliding-window evaluation protocol with a stride of 1, ensuring predictions at exactly the same timestamps. Specifically, CoLP propagates latent states between non-overlapping windows separated by L time steps and maintains independent latent states for each window offset, allowing predictions at every time step. MSE and MAE are computed over the same prediction starting points and prediction horizons for all models, ensuring a fair comparison under identical evaluation conditions. We include these details in the revised manuscript (Appendix A.1).
[Response to W2] Thank you for pointing this out. The reported values are not inconsistent, as the differences arise from different experimental settings. As stated in Section 5.1, Table 1 reports the best performance selected from multiple input lengths (i.e., input length is a hyperparameter and selected through validation), whereas Table 3 in the revised manuscript and all other ablation studies use a fixed input length of L=96. Therefore, the reported values are consistent with their respective experimental settings.
[Response to Q2] Thank you for this important question. To examine CoLP's stability during long-term operation, we evaluate its performance on the final 30% of the test stream with an extended range of inference propagation lengths Tprop∈1,2,4,8,32,128,∞.
As shown below, performance improves as Tprop increases and then stabilizes at longer propagation lengths, consistent with our findings in Section 4.5. In particular, the no-reset setting Tprop=∞ maintains strong performance, demonstrating that CoLP can effectively operate over long inference streams without requiring periodic resets. We attribute this stability in part to our training strategy and latent propagation design. The training segment length G=4 allows the model to learn how to accumulate and retain historical context across consecutive instances, rather than limiting context accumulation to four instances. As shown in Figure 5(a), G=4 provides a good balance between forecasting performance and training efficiency, as performance gains begin to saturate with longer training segments. Furthermore, our cross-attention-based propagation mechanism allows the current latent state to selectively incorporate relevant information from the accumulated historical context.
We include this additional analysis (Section A.6) and extend Figure 5(b) to cover the expanded range of propagation lengths in the revised manuscript.
We hope that our responses have addressed your concerns and clarified the key aspects of our framework. We would be happy to address any additional questions you may have.
Thank you for your valuable time.
Best regards,
Authors