- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes URGE for multimodal urban region representation learning. It uses Gaussian embeddings to estimate uncertainty and guide alignment and fusion. Experiments on NYC and London show improvements in prediction results and robustness to degraded inputs.
Critical strengths
-
The paper addresses a practical problem that urban data sometimes can be unreliable even when all modalities are available. Learning to handle this without downstream labels is useful.
-
URGE performs better than the tested baselines across the reported tasks in both cities. The masking and replacement experiments also provide evidence of robustness to degraded inputs.
Critical weaknesses
-
The PGA loss in Eqs. (6)–(7) has almost the same mathematical form as the negative mutual likelihood score in PFE (Shi and Jain, ICCV 2019). The paper does not cite or discuss this work, so it is unclear what is new in PGA.
-
UrbanFusion (ICML 2026) also learns spatial representations from similar modalities and handles incomplete inputs, but the paper does not compare with it. The paper also states that it evaluates 29 tasks, while only 8 city–task combinations are reported. The remaining results and the reason for selecting these tasks are not provided.
-
The results show that the model performs better under perturbations, but do not show whether its predicted variances actually identify unreliable observations. Maybe the variances simply work as learned fusion weights. A direct analysis of how they change when a modality becomes less reliable may help clarify this.
-
The ablation study changes multiple components simultaneously. Removing probabilistic modeling also changes the alignment loss and removes uncertainty-aware fusion and RFR. Removing uncertainty-aware fusion also removes RFR. So, it is difficult to tell how much each component contributes.
Questions for authors
- How does PGA differ from the existing PFE objective?
- Can the authors provide results for all 29 tasks and compare with UrbanFusion under similar settings?
- When one modality is degraded, does its predicted uncertainty increase and its contribution to fusion decrease?
- Can the authors test each component separately while keeping the rest of the model unchanged?
Invitation to Review and Discuss the Rebuttal
Dear Reviewer,
Thank you for your review. As the discussion continues, I’d welcome your thoughts on the authors’ response. If their reply answered your questions, a quick note to let them know would be appreciated. If anything remains unclear, please feel free to ask a follow-up question.
Best regards,
Area Chair