- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes NARA, a self-supervised representation learning framework for heterogeneous geospatial entities. NARA introduces topology-aware spatial attention and anchor-conditioned regularization. Experiments on three downstream tasks demonstrate consistent improvements over existing baselines.
Critical strengths
-
The method integrates semantic, geometric, and topological information in a framework.
-
The experimental results are strong across three downstream tasks. The ablation studies further support the effectiveness of the proposed components.
Critical weaknesses
-
The authors have clearly reduced the line spacing to include more content into main text. I am not sure if this complies with ICLR policy.
-
The experiments section states CityFM as specifically designed for certain downstream tasks. However, CityFM is a self-supervised framework for learning geoentity representations. The claimed novelty of heterogeneous entity representation learning is also overstated.
Questions for authors
-
See weakness.
-
The topology-modulated distance bias consists of two additive terms, but their individual contributions are not separately validated through ablation studies.
4 comments
Q2. The topology-modulated distance bias consists of two additive terms, but their individual contributions are not separately validated through ablation studies.
Thank you for this comment. We separately ablate the topology-specific offset and the topology-modulated distance term .
| Pairwise attention bias | Macro-F1 ↑ | Weighted-F1 ↑ | Accuracy ↑ |
|---|---|---|---|
| No pairwise bias | 70.92±1.4 | 91.45±0.3 | 91.97±0.3 |
| Topology intercept only | 72.73±1.4 | 92.38±0.3 | 92.75±0.3 |
| Topology-modulated distance RBF only | 74.82±1.4 | 92.93±0.3 | 93.31±0.2 |
| Topology intercept + topology-modulated distance RBF (Full NARA) | 74.30±1.2 | 92.76±0.3 | 93.13±0.3 |
The topology intercept improves Macro-F1 by 1.81 points when used without the RBF term ( =0.0078). The topology-modulated RBF term improves Macro-F1 by 3.91 points without the intercept ( <0.001) and by 1.57 points when added to the topology-only model ( =0.021). Adding the intercept to the RBF-only model changes Macro-F1 by -0.53 points, which is not significant ( =0.217). This finding is consistent with our response to Reviewer H9R4 W1. Under the current distance measures (i.e., minimum distance between complete geometry), the relation-specific RBF term can already represent relation-specific values at d=0. We use both terms in the general formulation because it accommodates additional topological relations and alternative distance measures with within-relation distance variation, and because each term independently improves performance. The topology-modulated RBF term provides the largest improvement, and the full two-term formulation performs comparably to the RBF-only variant. We added the ablation results and clarified this interpretation in Appendix C.4.1 (Line 1125 - 1177).
Thanks for your detailed clarification, which addresses my concerns. I therefore raise my score.
Thank you very much for your reconsideration and for raising your score to weak accept. We are pleased that our clarifications have addressed your concerns.
We sincerely appreciate the reviewer for recognizing NARA’s novelty in contextual representation learning with semantics, geometry, and their spatial relations, as well as NARA’s strong performance across tasks. We appreciate the concerns regarding presentation, our positioning relative to CityFM, and the parameterization of the attention bias. We carefully addressed each point below.
Thank you for bringing this formatting concern to our attention. Our submitted manuscript included local spacing adjustments around several section headings to satisfy the 9-page submission limit. To fully address the concern, we removed all spacing adjustments and restored the default spacing specified by the official ICLR template throughout the manuscript. We have carefully verified that the revised manuscript remains within the permitted 10-page limit.
Thank you for this helpful clarification. We agree that CityFM is a state-of-the-art self-supervised framework for learning geoentity representations. We note that CityFM uses separate encoders for each geometry type, objective, and feature pipeline, all tailored for specific downstream tasks, whereas NARA applies a shared contextual encoder and shared self-supervised objectives across points, polylines, and polygons.
CityFM designs and uses encoders and pretraining objectives targeted to each evaluated downstream task (i.e., not task-agnostic). For example, one of CityFM’s pretraining objectives aligns an image representation of a rasterized building footprint with the semantic representation of the same building. The underlying assumption is that rasterized images help capture building shapes, and that building shapes matter for function classification. This objective would only work for downstream tasks that depend on polygon shapes (e.g., building classification), and would not work directly for points and polylines. Another example is that CityFM leverages participation in public transit routes to design contrastive learning on polyline embeddings, assuming that road polylines on shared transit routes have similar traffic speed, useful for mobility applications. Although CityFM effectively models task-relevant assumptions in pretraining objectives, design choices require redesigning pretraining objectives as new tasks emerge.
In contrast, NARA uses a task-agnostic self-supervised pretraining strategy. NARA applies the same objectives to points, polylines, and polygons rather than encoding task-specific assumptions into separate objectives. NARA learns contextual geoentity representations from complete geometry and semantics, as well as spatial relations across surrounding geoentities. This task-agnostic design is useful when a geoentity’s function depends not only on its isolated attributes or shape but also on its heterogeneous spatial context. For example, how a building polygon relates to nearby roads, POIs, and other polygons. With task-agnostic design, NARA improves traffic MAE from 3.20 to 2.93 under the matched CityFM protocol and building Macro-F1 from 69.34 to 74.30.
We view CityFM’s task-informed objectives and NARA’s task-agnostic objectives as complementary. CityFM representations can capture task-relevant information, and NARA contributes task-agnostic geoentity contextualization. Future work could further investigate ways to combine these design principles, e.g., using NARA embeddings as universal base representations and further fine-tuning with a task-relevant training objective. We have revised the manuscript to avoid claiming novelty for heterogeneous geoentity representation learning itself. We also added a statement regarding CityFM in the experiment section (Section 5; Line 357 - 360). We thank the reviewer for the opportunity to clarify this distinction and for facilitating this valuable discussion.