- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper addresses traffic time-series imputation under random, single-sensor interval, and multi-sensor block missingness. PAST has two components. The Graph-Integrated Module (GIM) propagates observed measurements over a temporal graph defined by the observation mask and then over the road network. It uses interval-aware edge dropout to reduce reliance on nearby observations. The Cross-Gated Module (CGM) encodes sensor identity and calendar context, injects these features into the GIM layers, and predicts a residual that is added to the GIM estimate at missing entries.
Critical strengths
-
The primary and auxiliary distinction is well matched to structured missingness: the GIM uses measurements where they are available, while per-entry calendar and sensor context is injected into its layers to support estimates inside a gap.
-
Interval-aware edge dropout is a targeted regularization choice. It encourages the model to rely less on the nearest observations while retaining the possibility of using local evidence, which fits the paper’s motivation for handling long gaps.
-
The model keeps the road graph sparse during spatial propagation and uses repeated one-hop products instead of forming dense graph powers. This gives the design a clear computational advantage for networks with many sensors and relatively few road edges.
Critical weaknesses
-
Every missing receiver has the same incoming temporal neighbors: all observed steps and the CGM context node. The aggregation therefore does not explicitly weight observations by their temporal distance to each target. Target-specific distinctions must instead arise through the node features and CGM injection, and the paper does not establish how well this handles different temporal relationships to the observed data.
-
The residual-learning procedure is not fully specified. The CGM target depends on the current GIM prediction, but both losses are stated to be minimized together. If gradients from the CGM loss pass through the GIM prediction, the training is not equivalent to fitting a residual after a fixed primary model, as suggested by the gradient-boosting interpretation. The resulting interaction between the two branches is unclear.
-
The residual branch is trained from observed entries but is applied only at missing entries. The paper does not describe a calibration or consistency constraint that ensures residuals learned on observed locations transfer to entries with different mask-dependent support. This may be especially relevant for long gaps, where the GIM feature distribution differs substantially from that at observed entries.
-
The auxiliary branch uses sensor identity and calendar embeddings but no dynamic exogenous signals. It can represent recurring profiles, but it has no direct input for incidents, weather effects, special events, or other nonrecurring regime changes inside a gap. The measurement branch can mitigate this when nearby evidence remains, but the limitation is most relevant to the long and wide gaps that motivate the method.
-
CSDI, ImputeFormer, and OPCR are evaluated on one representative setting for each missingness type rather than across the full range of random rates and gap lengths or widths. Their relative performance over the broader configuration grid therefore remains unclear, which limits the strength of the comparison with recent methods.
Questions for authors
-
For two missing time steps with different temporal distances from the observed entries, what part of the GIM representation makes their primary estimates different before CGM context is injected? Please clarify whether the implementation includes any target-dependent temporal encoding or weighting.
-
Are GIM predictions detached when forming the CGM residual target, or are both branches optimized jointly through that target? Please state the exact gradient path and explain how it relates to the gradient-boosting interpretation.
-
What criteria were used to select the representative settings for CSDI, ImputeFormer, and OPCR? Were these settings chosen to reflect the range of gap severities within each missingness type?
5 comments
Response to Reviewer jz2A (Part 2/3): Gradient Path and Transfer of the Residual
Q2 / W2: "Are GIM predictions detached when forming the CGM residual target, or are both branches optimized jointly through that target? Please state the exact gradient path and explain how it relates to the gradient-boosting interpretation."
The GIM prediction is detached. The revised Eq. (2) reads and , where denotes stop-gradient. The exact gradient path is:
| Loss | Updates GIM | Updates CGM |
|---|---|---|
| Yes | Yes, through the context injected into every GIM layer | |
| No (stop-gradient) | Yes |
The interaction through the injected context is the intended coupling between the two modules. As the reviewer points out, both objectives are minimized jointly, and the residual target moves as GIM is updated, so the training is not stage-wise gradient boosting. Section 4.1 now names the scheme joint residual learning with a stop-gradient and states this gradient path, and the introduction uses the same name.
W3: "The residual branch is trained from observed entries but is applied only at missing entries. The paper does not describe a calibration or consistency constraint that ensures residuals learned on observed locations transfer to entries with different mask-dependent support. This may be especially relevant for long gaps [...]"
The residual branch is supervised on gap-like entries. At every training step, a random subset of the observed entries is additionally hidden from the model input while remaining in both losses:
- under fiber and block configurations, a contiguous interval is hidden in half of the sensor series of each batch;
- under random configurations, 10% of the entries are hidden at random.
At these hidden entries, GIM must infer the value from support that mimics real gaps, including long gaps, and the residual branch learns to correct exactly these estimates. The residual branch is therefore trained on the same kind of entries that it corrects at inference. The revised Section 4.4 describes this procedure. The real-world evaluation supports the transfer: on real sensor failures, adding the residual branch to the injection-only model lowers RMSE from 0.497 to 0.458 (see our response to F7jZ).
Response to Reviewer jz2A (Part 3/3): Exogenous Signals and Representative Settings
W4: "The auxiliary branch uses sensor identity and calendar embeddings but no dynamic exogenous signals. It can represent recurring profiles, but it has no direct input for incidents, weather effects, special events, or other nonrecurring regime changes inside a gap. [...]"
We agree with the reviewer that calendar and sensor-identity context captures recurring profiles, and that non-recurring events such as incidents, weather or special events are outside its scope. The revised Section 6 now states this explicitly. The CGM interface is generic: any per-entry exogenous signal can be embedded and gated in the same way as the calendar features, without changing the rest of the model. The standard benchmarks used here and in prior work (METR-LA, PeMS-Bay and LargeST) do not provide such signals, and we consider them a natural extension of PAST.
Q3 / W5: "What criteria were used to select the representative settings for CSDI, ImputeFormer, and OPCR? Were these settings chosen to reflect the range of gap severities within each missingness type?"
The criterion was one configuration per missingness type at the common missing rate of 0.4, fixed before any results were obtained: random r=0.4, fiber l=24 and block (48,10). The reason for evaluating a single configuration per type is computational cost, in particular CSDI's diffusion sampling over 27 configurations and two evaluation settings.
These settings cover both ends of the severity range. Fiber l=24 is the shortest fiber gap, and block (48,10) has the widest spatial span. Because the margin of PAST grows with gap length, the shortest fiber gap is the fiber setting least favorable to PAST; even there, PAST leads all three recent methods out of sample on METR-LA.
Table B. Out-of-sample RMSE on METR-LA in the representative configurations (original Table 1).
| Method | Random r=0.4 | Fiber l=24 | Block (48,10) |
|---|---|---|---|
| CSDI | 0.2711 | 0.4774 | 0.5499 |
| ImputeFormer | 0.3524 | 0.4399 | 0.5417 |
| OPCR | 0.2874 | 0.5303 | 0.5510 |
| PAST | 0.2108 | 0.3083 | 0.3442 |
How the methods behave as gaps become longer and wider is covered by the seven established baselines, including the traffic-oriented GRIN and STCPA, on all 27 configurations. There, PAST is best in 53 of 54 settings, and its margin grows with gap length and spatial span. The revised Section 5.1 states this selection criterion.
We hope these responses address the reviewer's concerns. We would be sincerely grateful if the reviewer would take them into account in the final assessment, and we would be glad to provide any further clarification during the discussion period.
Response to Reviewer jz2A (Part 1/3): Target-Specific Temporal Weighting
We sincerely thank the reviewer for the detailed and technically precise review. We are encouraged that the reviewer found the primary/auxiliary distinction well matched to structured missingness, interval-aware dropout a targeted regularization choice, and the sparse spatial propagation computationally advantageous. The questions helped us state several parts of the method much more precisely. We answer each point below, and all changes are included in the revised PDF (changes in blue).
Yes, the implementation includes target-dependent temporal weighting. Every missing receiver has the same set of sources (the observed steps and the context node), but the weights on these edges are not shared. The temporal adjacency is a learnable L×L matrix Θ, indexed by the target step u and the source step v, together with a learnable weight θu for the context vertex:
[AT]uv=Θuv if step v is observed, θu if v is the context vertex, and 0 otherwise.
Each row is normalized by the sum of absolute weights over the available sources. Each target therefore has its own weighting over the observed steps, and this weighting encodes temporal distance. The case definition in the original Section 4.2 gave the support of this matrix; the revised Eq. (3) writes out the learnable weights on it.
The learned weights show this directly.
Table A. Mean ∣AT[i,j]∣ by temporal distance ∣i−j∣ in the first forward temporal layer, and the share of each row's weight within one hour (∣i−j∣≤4; uniform weighting gives 0.088). New Appendix M.
Three observations follow:
Two missing steps at different distances from the observations therefore aggregate different observations with different weights, and obtain different primary estimates before any CGM context is injected.