- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
In time series forecasting, text can serve as exogenous information that guides predictions alongside the numerical look-back window. However, injecting unreliable text can mislead the forecasting model. To address this problem, the authors propose DynaGuard, which has three components: Time-Slice Context Compression (TCC) compresses the text within each time interval, Context-Adaptive Temporal Bias (CATB) generates an attention bias for each interval embedding and, Content-Aware Gated Injection (CAGI) generates a correction term for each numerical token. Because the final correction term is simply added back to the numerical token, DynaGuard is compatible with a wide range of backbones. Experiments show that DynaGuard reduces negative transfer and improves forecasting accuracy, and ablation studies confirm the contribution of each component.
Critical strengths
- The paper targets an important problem in multimodal time series forecasting: how to reduce the impact of irrelevant textual information on forecasting accuracy.
- The empirical results show that the approach works with several numerical forecasting architectures, which demonstrates its robustness.
- The paper is well written and easy to follow, and the added case study helps explain how the method works.
Critical weaknesses
- In the experiments, the main perturbation test randomly replaces text with a placeholder indicating missing information, across three domains. This does not establish resilience to plausible but incorrect text.
- Although six backbones are used, the evaluated tasks are all univariate, so it is unclear how well DynaGuard handles multivariate time series.
- When content and query are fixed, CATB imposes a relevance that decreases monotonically with the age of the text. This may be unsuitable for events whose effects emerge after a delay or recur periodically (for example, when a stock market is closed over the weekend, news from Friday may only matter on Monday).
Questions for authors
- Could the authors please address the three points raised in the "Weaknesses" section?
- In the TCC module, does the learnable query carry any semantic meaning?
- In the CATB module, could the authors provide an intuitive explanation of the learned bias, or use a case study to show its value distribution and how it affects the results?
- The layout of the captions in Figures 3 to 5 should be improved to enhance readability.
5 comments
Response to Reviewer (kRgD) — Part 2/3
W3 | Weakness 3 (Question 1): CATB Monotonic Decay, Delayed Effects, and Recurring Events
With content and query fixed, the CATB bias decreases with historical distance. The monotonicity concerns the temporal bias, not the forecast response, which also depends on query–context compatibility, the CAGI gate, and the prediction head (Figure 26). Moreover, and are predicted for each slice, so slices of the same age can receive different biases: content can override the age penalty, and the weighting across slices need not be monotone.
The main-paper case study (Figure 9) shows this behavior. In the displayed run, two reports describing past price conditions receive substantial attention, and masking them increases RMSE by 11.4% and 2.4%, although they lie six and seven weeks before the forecast. CATB, in contrast, reduces mean attention to a topically related but non-predictive report from 16.2% to 10.6%, and removing that report lowers RMSE. Relative influence therefore follows content as well as age.
Delayed effects are examined in Appendix K. For D events, whose effect starts eight steps after publication, retaining the bulletin lowers active-phase MSE by 5.48 on PatchTST and 5.45 on iTransformer (×10⁻⁴) and lowers the full 64-step MSE on both backbones (Table 95; Figure 28(d)). On both Signed and Delayed, CATB also lowers error relative to a shared decay within the same logarithmic family at short horizons (Figure 23), and has lower horizon-averaged MSE than both linear-decay alternatives in all nine real-world domains (Table 55). DynaGuard may capture periodic effects implicitly through changing numerical queries and their interactions with text. CATB’s bias itself decreases monotonically with age for fixed content and query and does not explicitly model recurring peaks in an event’s relevance. Appendix A discusses this limitation and identifies more flexible temporal functions as a direction for modeling these patterns explicitly.
Report-removal effects for D (Delayed), — Table 95.
| Backbone | Phase / steps | Keep MSE (×10⁻⁴) | Remove MSE (×10⁻⁴) | ΔMSE (×10⁻⁴) |
|---|---|---|---|---|
| PatchTST | Wait 1–7 | 5.233 ± 0.461 | 2.489 ± 0.172 | −2.743 [−3.174, −2.312] |
| PatchTST | Active 8–39 | 9.838 ± 0.775 | 15.315 ± 1.237 | 5.477 [4.234, 6.720] |
| PatchTST | After 40–64 | 12.788 ± 1.033 | 12.189 ± 0.833 | −0.599 [−1.023, −0.175] |
| iTransformer | Wait 1–7 | 5.231 ± 0.882 | 2.778 ± 0.206 | −2.453 [−3.436, −1.470] |
| iTransformer | Active 8–39 | 8.813 ± 1.059 | 14.262 ± 1.541 | 5.449 [3.491, 7.408] |
| iTransformer | After 40–64 | 14.876 ± 1.755 | 13.550 ± 1.041 | −1.326 [−3.654, 1.002] |
Note: 14 notices, five seeds. Keep/Remove: mean ± sample SD. ΔMSE = Remove − Keep, mean [95% t interval]; positive favors retaining the notice.
Response to Reviewer (kRgD) — Part 3/3
Q2 | Question 2: Semantics of the Learnable TCC Query
The learnable query learns a preference for selecting text content relevant to the forecasting task. In Equation 5, each head projects it as and matches this vector against text keys. The frozen pretrained input embeddings provide token representations, while and the attention projections learn from forecasting error. The query is shared across time slices, and its attention distribution depends on the tokens present in each slice. Its interpretation therefore concerns the content it selects, without requiring individual heads to correspond to predefined semantic categories. Replacing it with a query derived from numerical history raises horizon-averaged MSE in all nine domains on iTransformer (Table 48, Appendix F.1). This result supports using a shared query for compression, with numerical conditioning applied during subsequent retrieval.
Q3 | Question 3: Interpretability of the Learned CATB Bias
The learned bias cannot be read directly from real-world forecasts, where text content, text age, and numerical history vary together. We therefore analyze it on the controlled semi-synthetic data (Section 4.6, Appendices K–L), where the event and its text are known and one factor can be varied at a time.
The bias has two learned components. Salience determines the importance of a slice's content; decay determines how quickly this weight decreases with age. On Signed, a sustained event (A1) receives positive salience (1.44 PatchTST, 1.34 iTransformer) and the missing-text placeholder negative, whereas a pulse (B1) has lower salience and a larger (Table 88). For PatchTST, the bias of A1 relative to the placeholder remains positive at all ages, whereas that of B1 changes from positive to negative with age (Figure 25).
We measure the forecast response to one A1 notice while holding weights, numerical histories, other text, and targets fixed. The response is the forecast with the notice minus the forecast with it removed. We compare notice ages 0 and 64 with the CATB bias enabled and disabled; the two ages give identical responses when the bias is disabled (Figure 26). The age contrast is the age-0 versus age-64 response difference with CATB enabled, minus the corresponding difference with CATB disabled. For A1, the paired contrast is 15.24 [3.33, 27.14] for PatchTST and 23.00 [18.54, 27.46] for iTransformer (×10⁻³ in target units; Table 93). Brackets give pointwise 95% intervals over five seed means, each averaging 37 fixed histories. Both intervals exclude zero, supporting a larger effect of text age over steps 5–16 than over steps 33–64. In this controlled experiment, CATB changes how text age affects corrections across the forecast horizon.
Q4 | Question 4: Caption Layout for Figures 3–5
We thank the reviewer for this suggestion. The captions of Figures 3–5 have been revised: all three use a common ragged-right layout with matched margins and no hyphenated line breaks, and each states its statistic—first-place counts over the 96 settings, including ties (Figure 3); wins, ties, and losses over the same settings (Figure 4); mean error reduction over the original methods across the three domains (Figure 5).
Response to Reviewer (kRgD) — Part 1/3
We thank the reviewer for the careful reading and constructive comments. Below, we respond to each concern and question, drawing on the additional controlled experiments and analyses in the revised manuscript. All figure, table, and equation references follow the revised manuscript.
W1 | Weakness 1 (Question 1): Robustness to Fluent but Incorrect Text
We agree that text drop, which replaces text with the missing-text placeholder, tests missing text only; it does not establish robustness to fluent but incorrect text. The revision adds a controlled test of the latter case.
We use controlled semi-synthetic tests to isolate the effects of text content and timing (Section 4.6, Appendices K–L). Events with known direction, magnitude, and onset are added to a real-world Traffic series from the Autoformer archive, each paired with a fixed text template. On Signed, numerical inputs and targets are held fixed while the text undergoes type swap, subtype swap, or reversal of its temporal order. These interventions preserve well-formed text while changing the stated event or its temporal placement. Each intervention increases error (Figure 24, Table 87), showing that the forecasts use event content and timing.
To assess performance under missing or temporally mismatched text, we compare perturbed DynaGuard with a Numerical-only backbone on matched origins and targets. On Base Traffic with PatchTST, horizon-averaged MSE remains below Numerical-only under text drop, within-window shuffle, and global shuffle at tested nominal rates up to 50% (Table 102).
In a separate experiment on Signed, Shuffle training augmentation improves performance under severe corruption. At 100% nominal corruption, it reduces MSE relative to clean-trained DynaGuard on identical test inputs by 7.75% (PatchTST) and 9.12% (iTransformer) under global shuffle, and by 4.48% and 5.39% under within-window shuffle (Figure 32, Table 82).
Base Traffic robustness with PatchTST — selected results from Table 102.
Note: MSE (×10⁻⁴), mean ± sample SD over five seeds after averaging four horizons. Nominal rates include placeholders; global shuffle is an offline perturbation.
W2 | Weakness 2 (Question 1): Multivariate Time Series
We thank the reviewer for raising this point. DynaGuard’s formulation accommodates multivariate numerical inputs and targets. The adapter applies residual corrections to numerical representations and gates the retrieved features at each token and feature channel (Equations 4 and 11). Across the six evaluated backbones, the same adapter design operates on variable tokens, patches, encoder states, and future segments.
Our evaluation studies text integration—content selection, temporal weighting, and correction strength—on single-target tasks, using the same task definitions for DynaGuard and all compared methods. Joint multivariate evaluation would examine how these textual corrections interact with dependencies across variables. We identify this evaluation as future work in Appendix A.