- Rating
- 2(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper investigates how to disentangle event effects from underlying temporal dynamics in event-aware time series forecasting, while also predicting the impact of known future events. The motivation stems from the fact that transient changes triggered by historical events may be erroneously propagated into the future by a model, a form of confusion that cannot be easily resolved by merely incorporating event information as input. To address this, we employ a shared event-response function to strip away the effects of historical events prior to forecasting, and subsequently inject the responses of future events into the baseline predictions. Experimental results demonstrate that this approach achieves the lowest normalized mean absolute error across five benchmark datasets.
Critical strengths
1.The study addresses the issue of the erroneous extrapolation of historical event effects, with a clear research motivation.
2.It employs a unified approach, using shared event responses for both historical disentanglement and future injection resulting in a concise structure.
3.The effectiveness of the method is validated across five benchmarks, and key design components are examined through ablation analysis.
Critical weaknesses
-
Existing research has already addressed issues such as the erroneous extrapolation of historical event effects and the necessity of disentangling routine dynamics from event-driven effects. The present paper fails to clearly articulate what novel contributions it offers beyond these established approaches. Furthermore, the authors do not explicitly demonstrate the systematic prediction biases that arise in existing event-conditioned models following the conclusion of an event, nor do they adequately distinguish between genuine "tail effects" (lingering impacts) of an event and the erroneous extrapolation of event effects. Consequently, a mere reduction in overall prediction error is insufficient to justify the motivation behind the proposed method.
-
The fact that historical and future events belong to the same underlying process does not automatically imply that they share the same response structure. Moreover, the relative impact of an event may fluctuate based on demand conditions, weather, or operational circumstances; however, the response functions in this paper rely primarily on event type, intensity, relative timing, and the specific entity involved, offering limited capacity to capture context-dependency or synergistic interactions between multiple events. Additionally, because the model is trained solely based on the final prediction loss, the backbone and the event-specific branches can compensate for one another, which does not guarantee that the historical adjustments actually correspond to the intended disentanglement of event effects.
-
By halting gradients when an event is active, the model effectively forces the event-specific branches to absorb prediction errors, errors that may, in fact, stem from poorly modeled "routine" (non-event) dynamics. The current experiments do not sufficiently disentangle the respective contributions of the shared structural components versus the gradient-halting mechanism. Furthermore, while the method accounts for "pre-event" effects and "post-event" tail effects, the gradient-halting mechanism is triggered strictly by the binary status of the event indicator.
-
The primary experiments focus on comparisons with general-purpose predictors, lacking benchmarks against the most relevant existing methods, namely, those designed for event decomposition or historical filtering, as well as a baseline that employs a simple response lookup table (using the same backbone and training protocol). It is therefore unclear whether the observed performance gains stem from the decomposition structure itself or from the complex parameterization of the response functions. Additionally, existing comparisons between shared and independent response components fail to adequately control for differences in the number of parameters or the regularization strategies employed.
-
The semi-synthetic experiments rely on favorable conditions, such as stable multiplicative responses, independent scheduling, and non-overlapping events, thereby failing to rigorously test the model’s performance under scenarios involving context-dependency, overlapping events, or mismatches in the assumed response structure. Moreover, the analysis of event contexts defines windows based solely on whether an event indicator is active; however, since "pre-event" or "post-event" (tail) responses can persist even when the indicator is zero, this approach cannot accurately isolate genuine event effects from erroneous extrapolations.
Questions for authors
see weaknesses
8 comments
Rebuttal Part 2
W2. The fact that historical and future … does not automatically imply that they share the same response structure … limited capacity to capture context-dependency or synergistic interactions between multiple events … the backbone and the event-specific branches can compensate for one another..
Thank you for raising these concerns.
(i) Sharing a response function, not a fixed response. The two sides share one mapping from event conditions to responses rather than one response value: the ERF varies with event intensity, relative timing and entity, so each occurrence of the same event type can have a different response. If historical and future responses followed systematically different rules, learning separate ERFs for the two sides should perform better; the experiments show otherwise:
| Data type | Dataset | Metric | Shared | Independent | Half-independent |
|---|---|---|---|---|---|
| Real data | Ride-Hailing | Prediction MAE | 0.15696 | 0.15717 | 0.15691 |
| Real data | M5 | Prediction MAE | 0.09583 | 0.09825 | 0.09845 |
| Semi-synthetic | Ride-Hailing | Historical MAE after adjustment | 0.0207 | 0.0294 | 0.0299 |
| Semi-synthetic | M5 | Historical MAE after adjustment | 0.0118 | 0.0272 | 0.0277 |
Half-independent matches the parameter count of Shared. Sharing gives the best prediction on M5 and is on par on Ride-Hailing, and it clearly improves historical adjustment on both semi-synthetic datasets. Real-data parameter controls: Appendix D.2; semi-synthetic recovery: E.4.
(ii) Variation of relative impact with context. Continuous environmental variables, such as temperature, modulate the baseline through FiLM; localized weather events, such as rain and snow, enter the ERF as event inputs. The ERF does not additionally condition its response on recent demand levels, limiting its ability to represent this form of state dependence. In semi-synthetic experiments where the injected response depends on the recent demand level, Loki reduces future effect error relative to the zero-response reference by 70% (Ride-Hailing) and 79% (M5), compared with 93% and 94% under stable effects. We will state this limitation in the revised paper and leave context-conditioned response modeling to future work. Injection and full results: Appendix E.5.
(iii) Interaction among events. Concurrent events add in log space, which captures compounding impacts. Semi-synthetic future effect MAE for the combined response:
| Dataset | Overlap, no interaction | Overlap, with interaction | No interaction, training-RMS matched |
|---|---|---|---|
| Ride-Hailing | 0.0247 | 0.0438 | 0.0253 |
| M5 | 0.0164 | 0.0339 | 0.0167 |
An explicit interaction term raises the error, and the gap remains after matching the training perturbation RMS, so the multiplicative combination captures only part of the interaction. Injection and training-magnitude control: Appendix E.5.
(iv) Compensation between backbone and ERF.
- Gradient mechanism. The same forecasting loss backpropagates along three paths:
| Path | Backpropagation order |
|---|---|
| Future ERF | Loss → final forecast → future response |
| Backbone | Loss → final forecast → baseline forecast → Backbone |
| Historical ERF | Loss → final forecast → baseline forecast → Backbone → adjusted history → historical response |
The future-ERF path is the shortest, so the ERF learns the response rule mainly on the future side, and sharing applies it to the historical adjustment. The backbone keeps its gradients at all positions, so it learns routine dynamics from errors at event positions instead of leaving them to the ERF.
- Input constraint. The ERF acts only within the event-response support, including anticipation and carryover. It generates responses solely from event information, limiting its freedom to compensate for the backbone's errors on routine variation.
- Experimental evidence. On real data, the counterfactual without the event is unobservable, so we injected known event effects into real series:
Historical MAE follows before → after adjustment; future effect MAE follows zero response → multiplicative structure.
| Dataset | Injection condition | Historical MAE | Future effect MAE |
|---|---|---|---|
| Ride-Hailing | Multiplicative effects | 0.3333 → 0.0207 | 0.3284 → 0.0228 |
| Ride-Hailing | Events scheduled, no effect injected | 0 → 0.0097 | 0 → 0.0082 |
| M5 | Multiplicative effects | 0.1927 → 0.0118 | 0.2493 → 0.0155 |
| M5 | Events scheduled, no effect injected | 0 → 0.0052 | 0 → 0.0062 |
With an injected effect, Lift Out reduces the historical error by 93.8% (Ride-Hailing) and 93.9% (M5), and Kick In reduces the future-increment error by 93.1% and 93.8%, so the effect is captured by the ERF rather than absorbed by the backbone. In the no-effect control, both outputs remain close to zero, so the ERF rarely attributes routine dynamics to events. Settings, metrics and full results: Appendix E.1–E.4.
Rebuttal Part 3
W3.By halting gradients when an event is active, the model effectively forces the event-specific branches to absorb prediction errors, errors that may, in fact, stem from poorly modeled "routine" (non-event) dynamics. The current experiments do not sufficiently disentangle the respective contributions of the shared structural components versus the gradient-halting mechanism. Furthermore, while the method accounts for "pre-event" effects and "post-event" tail effects, the gradient-halting mechanism is triggered strictly by the binary status of the event indicator.
Thank you for pointing out that SG may force the event branch to absorb routine errors, that its contribution was not separated from the shared structure, and that it is triggered by binary event indicators. We have removed SG from the revised Loki; below, we compare SG on and off to explain this revision and examine whether the structural gains remain without SG.
(i) Why SG can make the event branch absorb routine errors. SG was intended to let the backbone learn routine variation and the ERF learn event responses. However, event positions may also contain baseline forecasting errors; SG prevents the backbone from correcting them while still letting the ERF update on them, so the event response can absorb baseline errors, as the reviewer points out. The same forecasting loss backpropagates along three paths; the last column shows the change when SG is enabled at event-active forecast positions in the submitted version:
| Path | Backpropagation order | With SG |
|---|---|---|
| Future ERF | Loss → final forecast → future response | Kept |
| Backbone | Loss → final forecast → baseline forecast → Backbone | Blocked |
| Historical ERF | Loss → final forecast → baseline forecast → Backbone → adjusted history → historical response | Blocked |
Because the blocking is set by the binary event indicator, it also does not cover anticipation and carryover positions. Without SG, the backbone and the ERF learn from the same loss at all positions.
(ii) Basis for removing SG. The table reports standardized prediction MAE (multi-seed mean ± sample SD) with SG off and on:
| Dataset | SG off | SG on |
|---|---|---|
| Ride-Hailing | 0.1570 ± 0.0003 | 0.1573 ± 0.0003 |
| TaxiBJ | 0.1128 ± 0.0016 | 0.1120 ± 0.0017 |
| M5 | 0.0958 ± 0.0011 | 0.0961 ± 0.0010 |
| Rossmann | 0.1365 ± 0.0028 | 0.1538 ± 0.0036 |
| Seoul Bike | 0.3238 ± 0.0208 | 0.3228 ± 0.0257 |
Removing SG lowers MAE on Ride-Hailing, M5 and Rossmann, while the TaxiBJ and Seoul Bike differences are within one seed SD. In semi-synthetic experiments under matched multiplicative injection, we fixed the shared multiplicative architecture, injected known multiplicative effects and varied only SG. Prediction and recovery metrics use the same valid positions within response support, including anticipation and carryover. Enabling SG does not improve the decomposition either:
All metrics are standardized MAE; each cell follows the order SG off → on.
| Dataset | Response-support prediction MAE | Historical MAE after adjustment | Future effect MAE |
|---|---|---|---|
| Ride-Hailing | 0.1694 → 0.1697 | 0.0207 → 0.0208 | 0.0228 → 0.0230 |
| M5 | 0.1128 → 0.1157 | 0.0118 → 0.0134 | 0.0155 → 0.0179 |
(iii) Structural gains do not depend on SG. In the final version without SG, full Loki still outperforms Direct Fusion, which feeds events directly into the forecast (Ride-Hailing 0.15696 vs 0.16124, M5 0.09583 vs 0.10257), and the shared ERF still outperforms separate ERFs for history and future (M5 0.09583 vs 0.09825). The gains of Lift Out/Kick In and sharing therefore do not come from SG.
The complete structural comparisons without SG are reported in revised Table 2; parameter-budget comparisons of shared and independent ERFs are provided in Appendix D.2.
Rebuttal Part 1
(i) Technical advance and practical benefits.
Loki is a simple, jointly trainable event pre- and post-processing module: the backbone learns routine dynamics from event-adjusted history, and responses are restored from future event schedules. It is compatible with different backbones and, with a lightweight structure, achieves the lowest MAE on all five benchmarks; on Ride-Hailing it uses only 0.27M parameters, about 86% below the median of the 15 neural baselines (Appendix C.1). It addresses three connected needs:
Loki also has lower MAE than the added SPADE, CEDAR, AutoARIMA-X, log-linear, Prophet, NeuralProphet and NBEATSx baselines on all five datasets (Table 1).
(ii) Erroneous extrapolation in existing event-conditioned models.
Separating genuine tails from erroneous extrapolation. Event end does not imply effect end. We select windows where a historical event has ended and demand has largely recovered: relative to a non-event reference for the same entity and time of week, the post-event observed deviation is at most half the historical deviation. This allows residual changes; we count forecasts that extend the historical anomaly beyond the observed residual. Agreement in at least 4/5 seeds is required for stochastic models; deterministic models use their single result.
Rate in model outputs. We apply the same screening to all five datasets. M5 has no test window with the relevant event ending before the forecast origin; Seoul Bike has only one eligible sample. We therefore report the other three datasets. All rates and replacement counts: Appendix D.10.
On TaxiBJ, most neural models, including TimeXer, TiDE and DAG, exceed 93%. All diagnostic windows come from one post-Qingming forecast date (2016-04-05).
For qualifying samples, replacing event-period observations reduces bias more effectively than replacing non-event positions, supporting historical event inputs as a contributor to erroneous extrapolation. This evidence comes from controlled input checks, not overall accuracy differences; the normal reference is not causal ground truth for event effects.
(iii) Loki under the same diagnostic. On TaxiBJ, Loki's rate (13.9%) is far below most neural models and no pair meets the replacement criterion. On Ride-Hailing and Rossmann, Loki ranks 2nd and 5th of 19 models, comparable to the better models, so it reduces but does not eliminate the problem. AutoARIMA-X and Prophet show low rates on TaxiBJ but much higher overall error (0.1718 and 0.2040 vs 0.1128). Post-event 24-hour MAE ranks Loki 1st on Ride-Hailing and Rossmann and 3rd on TaxiBJ; Five-dataset MAE and ranks: Appendix D.10.