- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes Graph Hierarchical Recurrence (GHR), a graph learning framework designed to improve out-of-range generalization in long-range tasks. GHR integrates recurrent computation with low-level and high-level message passing, where the high-level graph corresponds to the previous low-level graph pooled into a coarser graph, and the low-level graph for the next iteration is unpooled from the high-level one. The authors introduce in-range and out-of-range generalization and demonstrate that GHR outperforms flat-GNN baselines in long-range tasks.
Critical strengths
- The paper is well-written, enjoyable to read, and fits the chosen primary area.
- The idea of using hierarchical pooling and unpooling iteratively for the sake of reaching far-away nodes efficiently is interesting and novel. The experiments, results, and ablations are rigorous.
Critical weaknesses
- Even though the problem and the proposed solution are intriguing, I believe the experimental setup could be improved. To the best of my understanding, the RGG SSSP task uses a small synthetic dataset with a limited number of nodes (averaging 40 to 60). I think conducting a similar analysis on larger graphs would strengthen the paper's main claim, since the concept of "long-range interactions" is ill-defined in small graphs, such as the ones used in the paper.
- The recent SOTA method of Stable-ChebNet [1] is not included in the experiments. Please compare against this architecture specifically designed for long-range tasks.
[1] Hariri, Ali, et al. "Return of ChebNet: Understanding and Improving an Overlooked GNN on Long-Range Tasks." NeurIPS. 2025.
Questions for authors
- Have you analyzed the performance of GHR in both node-level and graph-level tasks in larger graph datasets?
- Have you compared against the most recent architectures specifically designed for long-range tasks, rather than simple GNN methods?
5 comments
Response to Reviewer PebH (References)
References
[1] Miglior et al., “Can You Hear Me Now? A Benchmark for Long-Range Graph Propagation”. ICLR (2026)
[2] Liang et al., “Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement”. ICLR (2026)
[3] Mathys et al., “LRIM: a Physics-Based Benchmark for Provably Evaluating Long-Range Capabilities in Graph Learning”. ICLR (2026)
Response to rebuttal by authors
Thank you for the rebuttal. Please report the pending results if they become available before the discussion period ends. I keep my score as is.
Response to Reviewer PebH
We thank the reviewer for highlighting that the hierarchical pooling and unpooling between two scales iteratively with the aim of reaching distant nodes effectively is an interesting and novel idea. Moreover, we also thank the reviewer for highlighting that the ablations performed are rigorous.
In the following we address the reviewer’s weaknesses and answer the questions.
W1
We thank the reviewer for this comment, which helped us spot a clarity issue in how we presented our experimental setup. The experiment with graphs of 40–60 nodes on average is the one in the paragraph "Small-distance regime OOR generalization". Its goal is specifically to test whether under-reaching occurs in fixed-depth architectures and uses a small-distance regime.
The full ablation study in the main text, however, is run on RGGs with 300-350 nodes. Because edges in random geometric graphs only connect spatially close nodes, shortest-path distances are large relative to graph size: at this scale, we compute distances between nodes being up to 40 hops apart which is usually considered a long-range regime in the current literature like ECHO [1].
We acknowledge that the graphs’ sizes were only reported in App., which made it hard to distinguish the two regimes apart. In the revised version we:
The changes are in Sec. 4.1 in lines 362-364.
W2
We thank the reviewer for the suggestion. In the original submission, we restricted our comparisons to the models reported in the respective benchmarks, which already span a variety of architectural families. We agree that Stable-ChebNet is a relevant baseline for long-range tasks, and we have added it to our experiments, using the official implementation and the configurations reported by the authors.
Below are MAE results on ECHO-Synth (mean ± std over 3 runs, lower is better) compared to GHR results, which are added to the revised manuscript:
Experiments on ECHO-Chem are currently running. We will report them here if they complete before the end of the discussion period. Otherwise they will be included in the final version of the paper.
The changes in the revised version are in Sec. 1, line 54-57 and in Tab. 1.
Q1
We thank the reviewer for the suggestion that complements the existing results. In order to analyze GHR performance on a Large Graph dataset we additionally evaluated GHR-GCN on City-Networks [2], a transductive node-level benchmark on real road networks with over 10^5 nodes per graph.
Following the manuscript methodology, we evaluated using GCN as backbone since it is in the original paper, allowing for a direct comparison. Due to the short times of the rebuttal, one more backbone and the rest of the cities will be included in the final version.
Accuracy is averaged across three independent seeds, hyper-parameters are fixed across the two cities: Hidden dimension = 64, T_H = 2 T_L = 8, graclus rounds = 4
In order to report training cost and needed resources on such large networks we additionally report full-graph training steps time and peak memory cost on GPU, showing how our framework, thanks to its linear complexity, adapts well to expensive datasets:
This additional experiment is referenced in the main text of the revised version in section 4.2 (lines 421-423) with all the results being added to the App. C.6.
Q2
We appreciate the reviewer’s interest in how we compare with recent long-range architectures. Our main benchmarks include both architectures designed specifically for long-range propagation and graph transformers. On ECHO (Table 1) we compare with rewiring (DRew), dynamical-system approaches (A-DGN, PH-DGN, SWAN and now Stable-ChebNet) and graph transformers (GPS, GRIT). On LRIM (Tab. 3) we compare with three different variants of GPS and with a virtual-node model.
Both ECHO and LRIM benchmarks were published at ICLR 2026, so their baselines show recent long-range architectures.