- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes ARCI-T, a traffic imputation method that keeps a deterministic recovery (LinearFill) as an explicit anchor and learns a residual correction on top of it. Experiments on four traffic datasets under random and structured missingness show the lowest MAE in almost all settings.
Critical strengths
- Simple, interpretable formulation with a guaranteed fallback to the deterministic reference. I think this approach is very practical.
- Consistent improvements across four datasets and both random and structured missingness.
- Extensive ablation studies are provided
Critical weaknesses
- According to the ablation studies, the gains seem driven mostly by the spatial component rather than the proposed mechanism. Please justify the motivation of the paper based on the experimental results.
- Standard graph-based imputation baselines (GRIN, PriSTI) are cited but not compared. I think these methods should be included as baselines.
- Only MAE is reported in the main tables. It would be better to report other metrics such as RMSE and MRE.
Questions for authors
Please see weakness above.
4 comments
W2 | Complete Five-Seed Comparison with GRIN
We agree that evaluating graph-based baselines on only a subset of missingness protocols gives an incomplete picture, and that a full multi-seed comparison against standard graph imputation models is necessary to properly evaluate our method against graph-based approaches. Accordingly, we completed all 80 evaluations () for GRIN, showing that ARCI-T achieves lower mean MAE in 14/16 settings—including all 8/8 structured missingness settings (Mixed25 and Sensor25)—while also explaining the hardware memory constraints encountered with PriSTI.
The complete 5-seed MAE results across all 16 settings are presented in Table R10(a), where relative error reduction is computed as (positive values indicate lower MAE for ARCI-T).
Table R10(a) | GRIN Across All 16 Settings: MAE Mean Sample Standard Deviation
| Dataset | Protocol | ARCI-T | GRIN | ARCI-T Error Reduction |
|---|---|---|---|---|
| METR-LA | ER25 | |||
| METR-LA | ER60 | |||
| METR-LA | Mixed25 | +11.02% | ||
| METR-LA | Sensor25 | +12.31% | ||
| PeMS-BAY | ER25 | +6.20% | ||
| PeMS-BAY | ER60 | +4.58% | ||
| PeMS-BAY | Mixed25 | +3.59% | ||
| PeMS-BAY | Sensor25 | +3.27% | ||
| PEMS04 | ER25 | +1.20% | ||
| PEMS04 | ER60 | +1.06% | ||
| PEMS04 | Mixed25 | +3.53% | ||
| PEMS04 | Sensor25 | +2.65% | ||
| PEMS08 | ER25 | +5.82% | ||
| PEMS08 | ER60 | +4.18% | ||
| PEMS08 | Mixed25 | +4.40% | ||
| PEMS08 | Sensor25 | +4.36% |
Across all 16 settings, the only two exceptions are METR-LA ER25 and ER60, where GRIN's mean MAE is slightly lower by 0.0178 and 0.0232, respectively; across all structured missingness settings (Mixed25 and Sensor25), ARCI-T achieves consistent gains of up to +11.02% and +12.31% on METR-LA.
Note on PriSTI: Regarding the conditional diffusion model PriSTI that you also mentioned, we tried to include it in a full benchmark comparison; however, because global spatiotemporal attention combined with multi-step iterative diffusion denoising has quadratic memory overhead across 300+ graph nodes, running PriSTI across all 80 evaluations () frequently triggers out-of-memory (OOM) errors and requires compute time beyond our laboratory GPU capacity. To ensure broad baseline coverage, alongside our complete GRIN evaluation, we included diffusion/generative and recent spatiotemporal imputation models such as FENCE, GiFlow, and StamImputer in our experiments and discussions, and we will add the complete GRIN results as well as a dedicated discussion of PriSTI's architecture and computational cost to the revised manuscript.
W3 | Multi-Metric Evaluation: MAE, RMSE, MRE, and MSE
W3 | Multi-Metric Evaluation: MAE, RMSE, MRE, and MSE
We agree with your suggestion: relying on MAE alone can hide how a model handles large outlier errors and does not fully reflect reconstruction quality across different error metrics. To provide a more complete evaluation, we compiled 5-seed average results for MAE, RMSE, MRE, and MSE across all 16 primary settings, showing that ARCI-T achieves lower mean MAE and MRE in 15/16 settings and lower mean RMSE and MSE in 16/16 settings—reducing RMSE by 6.62% and MSE by 12.82% even on PEMS04 Sensor25 where MAEs are similar.
Table R11 | Multi-Metric Results Across All 16 Original Benchmark Settings (ARCI-T / Baseline per Cell)
| Dataset | Protocol | Original Benchmark Strongest Baseline | MAE | RMSE | MRE | MSE |
|---|---|---|---|---|---|---|
| METR-LA | ER25 | OPCR | 2.1181 / 2.3287 | 4.3029 / 4.5338 | 0.0418 / 0.0459 | 18.9723 / 20.5571 |
| METR-LA | ER60 | OPCR | 2.4351 / 2.7142 | 5.1519 / 5.5956 | 0.0480 / 0.0535 | 27.1056 / 31.3145 |
| METR-LA | Mixed25 | OPCR | 3.2387 / 4.2784 | 7.0348 / 9.6135 | 0.0642 / 0.0848 | 49.4899 / 92.5633 |
| METR-LA | Sensor25 | BRITS | 3.4722 / 4.4574 | 7.4073 / 9.5245 | 0.0689 / 0.0885 | 54.8948 / 90.7180 |
| PeMS-BAY | ER25 | OPCR | 0.6867 / 0.7781 | 1.3477 / 1.5440 | 0.0110 / 0.0125 | 1.8164 / 2.3849 |
| PeMS-BAY | ER60 | Linear | 0.8648 / 0.9773 | 1.7575 / 1.9750 | 0.0138 / 0.0156 | 3.0889 / 3.9009 |
| PeMS-BAY | Mixed25 | OPCR | 1.4817 / 1.8081 | 3.2686 / 4.0500 | 0.0237 / 0.0290 | 10.6852 / 16.4064 |
| PeMS-BAY | Sensor25 | OPCR | 1.6458 / 1.9898 | 3.5584 / 4.3182 | 0.0264 / 0.0319 | 12.6665 / 18.6546 |
| PEMS04 | ER25 | ATTST | 15.8302 / 16.6908 | 26.0394 / 26.8786 | 0.0742 / 0.0782 | 678.0570 / 722.4748 |
| PEMS04 | ER60 | Linear | 16.7568 / 18.7669 | 27.4088 / 30.6854 | 0.0786 / 0.0880 | 751.2475 / 941.5973 |
| PEMS04 | Mixed25 | BRITS | 20.6271 / 21.7861 | 32.6985 / 37.1210 | 0.0973 / 0.1028 | 1069.3093 / 1378.6993 |
| PEMS04 | Sensor25 | BRITS | 21.9462 / 21.8621 | 34.6281 / 37.0842 | 0.1036 / 0.1032 | 1199.2053 / 1375.5825 |
| PEMS08 | ER25 | ATTST | 11.4385 / 13.0019 | 18.8336 / 20.1510 | 0.0499 / 0.0567 | 354.7077 / 406.0781 |
| PEMS08 | ER60 | Linear | 12.4842 / 14.4066 | 20.1022 / 22.4687 | 0.0544 / 0.0628 | 404.1057 / 504.8494 |
| PEMS08 | Mixed25 | BRITS | 16.2881 / 18.5288 | 26.0279 / 31.9534 | 0.0715 / 0.0813 | 677.7251 / 1021.3238 |
| PEMS08 | Sensor25 | BRITS | 17.2828 / 18.9193 | 27.3970 / 32.7537 | 0.0757 / 0.0829 | 750.6318 / 1073.1410 |
To compare multiple error metrics on the exact same method pairs, Table R11 keeps the strongest external baseline identified for each setting in the original benchmark (while comparisons with the newly added GRIN baseline are presented separately in Table R10(a)). PEMS04 Sensor25 clearly shows the value of multi-metric evaluation: while ARCI-T and BRITS have very similar 5-seed mean MAEs (21.9462 vs. 21.8621), ARCI-T reduces RMSE by 6.62% (34.6281 vs. 37.0842) and MSE by 12.82% (1199.2053 vs. 1375.5825), showing much stronger suppression of large outlier errors. Reporting MAE alone would miss these gains in squared error metrics. We will include these complete multi-metric results and analyses in the revised manuscript.
Manuscript Revision Guide for Reviewer yWyk
Manuscript Revision Guide for Reviewer yWyk
Thank you again for your valuable feedback. Following up on the experimental results reported in our response above, we have uploaded the revised manuscript (with all additions highlighted in blue). Below is the exact mapping of your three concerns to the sections, pages, and tables added or updated in the revised PDF:
-
Regarding W1 (Clarifying the role of the spatial component
CorrTopKand isolating the incremental contribution of the proposed acceptance mechanism):- Section 4.3 (Page 9, Lines 432–452, New Table 7) & Appendix C.7 (Page 25, Lines 1345–1349): Clarified in both the main text and appendix that bypassing
CorrTopK(w/o CorrTopK) alters the upstream spatial representation consumed by both the residual proposal head and the acceptance gate, and introduced the independently trained ungated variant G1 ( fixed throughout training and evaluation), which retains the exact same anchor andCorrTopKspatial backbone. - Appendix C.1 (Page 22, Lines 1178–1179; Page 23, Table 15) & Appendix C.5 (Page 24, Lines 1286–1295; Page 25, Lines 1313–1330, New Table 20): Added the formal definition of G1 (distinguishing it from the inference-only
All-Rintervention) and Table 20, reporting five-seed paired differences (), ordinary 95% confidence intervals, and unadjusted two-sided paired -test -values confirming that full ARCI-T outperforms from-scratch G1 across all 20/20 paired seed runs (raw p < 0.01across all four settings, remaining significant at under a Holm step-down check).
- Section 4.3 (Page 9, Lines 432–452, New Table 7) & Appendix C.7 (Page 25, Lines 1345–1349): Clarified in both the main text and appendix that bypassing
-
Regarding W2 (Adding full benchmark comparisons with graph-based imputation baselines
GRINandPriSTI):- Section 4.1 (Page 6, Lines 272–276) & Section 4.2 (Page 6, Lines 318–321): Integrated the 80-run () comparison with GRIN (Cini et al., 2022) into the main text, highlighting that ARCI-T achieves lower mean MAE in 14 of 16 settings and leads in all 8/8 structured missingness settings (
Mixed25andSensor25). - Appendix B.10 (Page 19, Line 1012; Page 21, Lines 1114–1116): Added full implementation and training details for
GRIN. - Appendix D.1 (Page 32, Updated Table 33; Pages 32–33, Updated Tables 35–38; Page 34, New Table 40): Updated the best-external summary (Table 33) and the complete protocol-level MAE tables for all four datasets (Tables 35–38) to include
GRIN, and added Table 40 reportingGRIN's five-seed MAE, RMSE, and MRE across all 16 settings. - Status of
PriSTI: As noted in our response,PriSTI(cited in Section 1, Page 1, Line 42) relies on global spatiotemporal attention combined with multi-step iterative diffusion sampling, which incurs prohibitive quadratic memory and runtime overhead on 300+ node graphs and could not be scaled to the full 80-run benchmark campaign under our GPU budget; therefore, we completed the full 80-run graph-imputer evaluation with GRIN while covering diffusion/generative baselines via CSDI, GiFlow, and FENCE.
- Section 4.1 (Page 6, Lines 272–276) & Section 4.2 (Page 6, Lines 318–321): Integrated the 80-run () comparison with GRIN (Cini et al., 2022) into the main text, highlighting that ARCI-T achieves lower mean MAE in 14 of 16 settings and leads in all 8/8 structured missingness settings (
-
Regarding W3 (Reporting additional evaluation metrics beyond MAE—
RMSE,MRE, andMSE):- Section 4.1 (Page 6, Lines 272–276), Section 4.2 (Page 6, Lines 321–323) & Appendix D / D.1 (Page 31, Lines 1622–1627, 1650–1655): Added formal definitions and main-text pointers for the secondary metrics (RMSE, MRE, and MSE), noting that against the fixed strongest comparator from the original benchmark, ARCI-T achieves lower mean MAE and MRE in 15/16 settings and lower mean RMSE and MSE in all 16/16 settings (distinct from the expanded
GRINpool). - Appendix D.1 (Page 32, Table 34; Page 34, New Table 40; Page 35, New Table 41 & Table 42): Added Table 41 (Page 35), providing the complete five-seed MAE, RMSE, MRE, and MSE comparison between ARCI-T and the fixed strongest original baseline in every setting (including
PEMS04 Sensor25, where ARCI-T lowers RMSE by 6.62% and MSE by 12.82%), alongside multi-metric tables forGRIN(Table 40) andDCCN-SPF/FENCE(Table 42).
- Section 4.1 (Page 6, Lines 272–276), Section 4.2 (Page 6, Lines 321–323) & Appendix D / D.1 (Page 31, Lines 1622–1627, 1650–1655): Added formal definitions and main-text pointers for the secondary metrics (RMSE, MRE, and MSE), noting that against the fixed strongest comparator from the original benchmark, ARCI-T achieves lower mean MAE and MRE in 15/16 settings and lower mean RMSE and MSE in all 16/16 settings (distinct from the expanded
W1 | Role of the Spatial Component vs. Contribution of the Proposed Acceptance Mechanism
Thank you for recognizing the practical utility of our approach and the effectiveness of our deterministic restoration reference. Below, we address your comments regarding the roles of the spatial component versus our proposed acceptance mechanism, graph-based imputation baselines, and multi-metric evaluation:
W1 | Role of the Spatial Component vs. Contribution of the Proposed Acceptance Mechanism
Thank you for pointing out that in our ablation study, a large portion of the performance gain comes from the spatial component. We agree with this observation, and we realize that our original manuscript did not explain clearly enough how the spatial modeling component and our proposed controlled-correction mechanism work together. To make our explanation self-contained without requiring a re-read of the paper: ARCI-T operates in two stages around a deterministic anchor (e.g., linear interpolation). First, the backbone extracts temporal features and cross-sensor spatial features—where the spatial component is implemented by our correlation-graph module (
CorrTopK), which aggregates information from the top-K correlated neighboring sensors—to predict a candidate residual correction relative to the anchor. Second, our proposed position-conditioned acceptance mechanism (the gating branch) evaluates local observational evidence to decide what fraction (G∈[0,1]) of that candidate correction should actually be applied at each missing position. To directly test whether our proposed acceptance mechanism still provides meaningful gains when the spatial component is held constant, we trained an ungated model (G1, which keeps the exact sameCorrTopKspatial component but fixes G≡1) from scratch. The results confirm that the spatial modeling component and the proposed acceptance mechanism play complementary roles, and that adding our acceptance mechanism consistently outperforms G1 across all 20/20 paired seed runs.Specifically, the spatial component (
CorrTopK) is indeed an essential source of information in ARCI-T—especially during long temporal gaps or whole-sensor outages where a target sensor has no nearby temporal observations of its own and must rely on neighboring sensors to reconstruct traffic states. However, our proposed acceptance mechanism is not intended to replace spatial modeling; instead, the spatial modeling component and the proposed acceptance mechanism address two different questions in our pipeline: the spatial component answers "what candidate correction can be proposed from neighboring sensors," whereas the proposed acceptance mechanism answers "how much of that proposed correction should be accepted and applied at each specific position."In our original ablation table, the
w/o CorrTopKvariant removed the spatial component entirely. Because both the residual proposal head and the acceptance gate take the upstream spatial features produced byCorrTopKas input, removingCorrTopKdegraded both branches at once and prevented the model from proposing informed spatial corrections in the first place. As a result, that ablation showed the necessity of spatial information, but could not isolate the standalone contribution of the acceptance mechanism. To properly separate the effect of our proposed acceptance mechanism from the spatial component, we trained the ungated control model G1 (G≡1) from scratch under our unified mechanism-analysis setup (fixed 100-epoch training selected by validation loss), keeping the exact same deterministic anchor,CorrTopKspatial component, and residual proposal network while removing position-conditioned gating.Table R8 | Controlled Comparison of the Proposed Acceptance Mechanism under an Identical Spatial Component (Trained from Scratch)
As shown in Table R8, across all four matched settings (5 random seeds per setting, 20 paired runs in total), the full ARCI-T model consistently outperforms G1 (1.5324 vs. 1.5503 on PeMS-BAY Mixed25; 1.6930 vs. 1.7432 on PeMS-BAY Sensor25; 21.7311 vs. 22.2097 on PEMS04 Mixed25; and 23.2781 vs. 23.8053 on PEMS04 Sensor25). In short, the spatial component supplies cross-sensor context to form strong correction candidates, while our proposed acceptance mechanism prevents applying full corrections blindly at positions where the local anchor is already accurate or where spatial signals are noisy. We will revise the motivation and ablation discussions in the manuscript to make this relationship clear.