- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes MOSAIC, a temporal graph learning framework that decouples temporal dynamics learning from structural graph learning. MOSAIC composes three complementary priors: temporal embeddings extracted from frozen time-series foundation models, local temporal-context summaries, and supra-Laplacian positional encodings that capture graph topology. These representations are integrated through a GNN with residual connections and trajectory-aware layer aggregation, allowing spatial relationships to be learned without backpropagation through time. The framework is evaluated on supervised node forecasting and classification tasks, where it achieves competitive or state-of-the-art performance across multiple benchmarks. The authors further investigate zero-shot cross-network transfer on the MiNT benchmark, demonstrating improved average AUC and reduced negative transfer across 20 unseen networks compared with recurrent temporal graph baselines.
Critical strengths
- The paper presents an interesting and well-motivated perspective on temporal graph learning by decoupling temporal representation extraction from structural graph learning. The proposed composition of pretrained temporal embeddings, local temporal statistics, and supra-Laplacian positional encodings provides a modular approach to incorporating complementary inductive biases, offering potential advantages in training efficiency and transferability across different graph domains.
- The experimental evaluation covers a diverse range of temporal graph learning tasks, including node-level forecasting, node classification, and zero-shot cross-network transfer. The supervised experiments demonstrate competitive performance against various representative baselines, while the evaluation on 20 unseen MiNT networks provides additional evidence of the framework's potential for cross-network generalization.
- The paper provides relatively comprehensive analyses of the proposed framework, including computational analysis and sensitivity to different pretrained time-series foundation models and supra-Laplacian configurations.
Critical weaknesses
- Insufficient validation of prior complementarity in zero-shot transfer. A central contribution of the paper is to utilize three complementary priors to improve cross-network generalization. However, the MiNT benchmark consists of featureless interaction graphs with constant node features. Under this setting, the temporal foundation-model embeddings and local temporal summaries receive essentially constant input signals, while the supra-Laplacian positional encodings contribute most. This raises the question of whether the observed transfer gains primarily originate from structural representations rather than the proposed composition of complementary priors.
- Insufficient characterization of dataset-dependent transfer behavior. Substantial performance discrepancies between single-network supervised training and zero-shot transfer on several datasets are observed, yet these observations are not adequately investigated. For example, MOSAIC achieves an AUC of only 0.098 under supervised training on BAG, compared with 0.972 under zero-shot transfer, whereas SDEX exhibits the opposite behavior, dropping from 0.954 to 0.454. Although the authors interpret it as evidence of substantial positive transfer, detailed dataset-specific evolving pattern analysis is expected.
- Limited supervised performance on forecasting benchmarks. Although MOSAIC achieves strong results on several node-level prediction tasks, its performance is less convincing on traffic forecasting benchmarks. Simply attribute them to architectural trade-offs and inductive biases is not enough to prove whether the performance gaps arise from the decoupling of temporal and structural learning.
Questions for authors
- Could authors further investigate the contributions of the three priors to zero-shot transfer on MiNT? An ablation study in the zero-shot setting would help clarify whether the observed improvements arise from all the proposed priors.
- Could authors provide further explanations for the substantial discrepancies between supervised and zero-shot performance on certain MiNT networks, particularly BAG and SDEX?
- Please provide more empirical evidence to clarify why architectural trade-offs and inductive biases are the major causes of MOSAIC's suboptimal performance in forecasting tasks.
3 comments
Response to W2, Q2, W3, Q3 and References
Regarding W2 and Q2
Thank you for raising this important question, which motivated a deeper investigation of the substantial discrepancies observed on BAG and SDEX. We analyzed three representative cases: strong positive transfer (BAG), near-zero positive transfer (HOICHI), and strong negative transfer (SDEX). The full dataset-specific analysis is provided in Appendix B.1.2 of the revision.
Our findings suggest that these discrepancies are not necessarily attributable to MOSAIC or training instability. In particular, similar effects occur across different architectures: pre-training improves the performance of all three models on BAG, while it also leads to negative transfer for HTGN on SDEX. Moreover, supervised performance is positively correlated across networks, suggesting that part of the difficulty is shared across models and stems from the underlying data.
We further find that these discrepancies are related to changes in the relationship between network activity and future growth across training and test periods. Although this relationship is predictive across most networks, its strength can vary substantially over time. For instance, it becomes much stronger on BAG, potentially explaining why zero-shot transfer substantially outperforms single-network supervised training. Conversely, this relationship nearly disappears on SDEX, providing a possible explanation for the substantial performance degradation under zero-shot transfer. To support this analysis, Figure 3 of the revised paper illustrates the evolution of network activity over time, which is particularly relevant because network activity directly defines the prediction targets.
Overall, these findings suggest that the contrasting behaviors on BAG and SDEX reflect, at least in part, network-specific temporal variability rather than systematic instability of MOSAIC. They also highlight that pre-training can provide substantial transfer gains, but does not guarantee positive transfer on every network.
Regarding W3 and Q3
Thank you for pointing out this issue. We show below that this gap comes mainly from the short context we provide to , rather than from our proposed decoupling of temporal and structural learning. is the embedding of a frozen pre-trained TSFM that processes its input in patches, so it needs a window long enough to contain meaningful patches in order to produce informative embeddings. Making the temporal component trainable would let the model adapt to short windows, but it contradicts the claims of our paper.
Moreover, as stated in [6], the time-then-graph paradigm is advantageous for expressivity compared to time-and-graph, so decoupling time from graph does not in itself restrict what can be represented. Instead, MOSAIC can exploit longer contexts at a flat training cost, since is precomputed (empirical runtime and memory analysis support this, see Appendix B.6). To support this discussion, we compare the performance of MOSAIC and baselines with its long context version, MOSAIC-LC, where is Chronos-Bolt small [3], since MOMENT reads at most 512 steps, and we set and , showing the results in the table below (Masked MAE$\downarrow$):
| Variant | PeMS03 | PeMS04 | PeMS07 | PeMS08 |
|---|---|---|---|---|
| Best baseline (Table 2) | 14.22 | 18.20 | 19.32 | 13.58 |
| MOSAIC | 14.68 | 19.08 | 19.68 | 14.09 |
| MOSAIC-LC (long context) | 14.36 | 18.49 | 19.25 | 13.53 |
The gap between MOSAIC and the best baseline of Table 2 is reduced from a mean of 0.55 to a mean of 0.08 over PeMS03, 04, 07, 08, when using a longer context. We added this analysis in Appendix B.9 (Table 17) of the revised paper. Thank you.
We thank you once again, and hope that our clarifications and additional experiments will lead to a reconsideration of your score.
References:
[1] Dwivedi and Bresson. A generalization of transformer networks to graphs. AAAI Workshop on Deep Learning on Graphs, 2021.
[2] Chen et al. Freeway performance measurement system: mining loop detector data. Transportation Research Record, 2001.
[3] Ansari et al. Chronos: learning the language of time series. TMLR, 2024.
[4] Ansari et al. Chronos-2: from univariate to universal forecasting. Technical report, 2025.
[5] Li et al. Open spatio-temporal foundation models for traffic prediction. ACM TIST, 2025.
[6] Gao and Ribeiro. On the equivalence between temporal and static equivariant graph representations. ICML, 2022.
Did our responses address your concerns?
Dear Reviewer yQ8C,
Thank you again for your careful review and valuable suggestions.
We hope that our responses have helped clarify the contribution of MOSAIC, the role of each prior in zero-shot transfer, the dataset-dependent transfer on MiNT networks such as BAG and SDEX, and the role of the temporal context in its traffic forecasting performance.
We would appreciate knowing whether our responses have addressed your main concerns, and we welcome any further questions or suggestions.
Best regards,
The Authors
Response to W1 and Q1
We thank you for your careful evaluation. We are encouraged by your recognition that the paper presents an interesting and well-motivated perspective on temporal graph learning, that the composition of priors provides a modular approach to incorporating complementary inductive biases, and that it offers relatively comprehensive analyses of the proposed framework. We address each point below, following our summary.
Overall summary of our responses: we include (i) an ablation on MiNT, complemented by new zero-shot traffic experiments where all priors are informative and a further ablation in this setting, (ii) a per-network analysis of the MiNT results showcasing the motivation behind strong positive/negative transfer, and (iii) an analysis on the performance limitation on traffic forecasting.
Regarding W1 and Q1
Thank you for this observation. Since MiNT contains featureless D-TDGs, Φs and Φf receive constant inputs, and Φp is the only prior that varies across nodes and snapshots. Ablating Φf or Φs on MiNT would thus only remove a constant input. Therefore, we ablate the choice of the structural prior. We replace the supra-Laplacian Φp with Laplacian Positional Encodings (LapPE) [1], computed on each snapshot independently. We pre-train MOSAIC with LapPE on the 64 MiNT networks and show in the table below the zero-shot test AUC$\uparrow$ on the 20 unseen networks, using the same hyperparameters of the full run (Appendix B.8 of the revision).
Replacing the supra-Laplacian Φp with a per-snapshot LapPE lowers the AUC from 0.744 to 0.676, showing that coupling consecutive snapshots matters on evolving topologies. However, given that this comparison does not include a scenario where we pre-train MOSAIC exploiting all three priors, we also conduct a zero-shot traffic forecasting experiment where all are used. Specifically, we pre-train MOSAIC in a leave-one-out fashion on PeMS-D{5,6,10,11,12} [2] and three of PeMS0{3,4,7,8}, and evaluate on the left-out dataset. In this experiment, Φf is Chronos-Bolt small [3] over wf=864 steps. We compare with graph-free baselines (TSFMs) and a recent spatiotemporal foundation model engineered for traffic prediction (OpenCity [5]). We report the performance (Masked MAE$\downarrow$) in the table below, in Table 2 and Section 4.3 of the revision, where † denotes that the pre-training corpus of the model contains the evaluation dataset, or traffic data from the same district:
MOSAIC outperforms all competitors where the setting is fully zero-shot, and is competitive with or outperforms them even where they have seen the target dataset during pre-training.
To fully answer your very important request, we ablate all priors as we did in Table 4, pre-training on PeMS-D{5,6,10,11,12} and PeMS0{3,4,8}, and evaluating zero-shot on PeMS07 (Masked MAE$\downarrow$, zero-shot column of Table 4 of the revision):
As in Table 4, Φf and Φs are the most important priors in this setting: removing Φf raises the error from 21.98 to 29.19, and removing Φs to 116.24, since without the window statistics the model cannot recover the scale of an unseen road network. In contrast to the supervised setting, Φp does not contribute here (21.71 without it): the road networks have a static topology, so the pre-training corpus contains only 8 distinct graphs, and their positional encodings carry little information to transfer.
Putting all together, (i) on MiNT, where the graphs are featureless and the topology evolves, the supra-Laplacian form of Φp outperforms a per-snapshot positional encoding, and (ii) in zero-shot traffic forecasting, the model relies on the TSFM embeddings and on the local window. Together with Table 4, this isolates the contribution of each prior in the supervised and in the zero-shot setting. We thank the reviewer for allowing us to run these further experiments, which made the characterization of our results stronger and positioned our contribution better.