- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes GDM, an RSSM-style world model for graph environments whose edges change over time. It keeps per-node and graph-level deterministic and stochastic states, plus a recurrent sampled adjacency matrix updated by Hard Concrete edge flips, and runs message passing on the predicted topology. It also proposes GDD, an MMD with a characteristic kernel over (topology, node features, graph features) for comparing predicted and true next-state distributions. On four synthetic environments (RGC, OD, SAR, CF), trained on 15–25 nodes and tested up to 1000 nodes, GDM outperforms Vanilla GWM, EA-GWM and G-RSSM on single- and multi-step GDD in most settings.
Critical strengths
-
This paper proposes a clear and clean edge dynamic design.
-
The experimental results show the performance of the proposed model against several baselines.
-
The gap between the proposed model and baselines is carefully analyzed.
Critical weaknesses
-
In Figure 5, GDM has much lower topology MMD than the baselines, while the node feature results are often similar. For CF at larger graph sizes, its graph feature result is worse. The comparison is difficult to interpret because the GWM baselines do not explicitly use the previous adjacency when predicting the next one. Since much of the graph usually stays the same between steps, I would like to see a simple baseline that copies the previous adjacency for topology evaluation, or GWM baselines that condition adjacency predictions on the previous adjacency. This would help show how much improvement comes from GDM’s architecture.
-
The paper argues that the joint-kernel term captures dependencies between topology and features. I could not find an empirical example where GDD gives a different useful conclusion from the separate MMD terms. Please compare GDD with an additive-only version and show how the joint-term weight affects the results.
-
In Table 5, setting β_h = 0 gives lower mean GDD at every tested size on SAR, including 0.835 versus 0.878 at 200 nodes. It also improves several CF and RGC results. Removing the graph state improves RGC at 100–200 nodes. Section 6.3 acknowledges these patterns, but more discussion about when these components help would be useful.
-
The size generalization result is mixed. SAR is the clearest positive case. On CF, it ties Vanilla GWM at 200 nodes. On RGC at 200 nodes, its mean is slightly higher than Vanilla GWM’s (1.175 versus 1.167), with substantial uncertainty. GDM remains better than the baselines on OD.
Questions for authors
Please respond to the above weaknesses.
6 comments
W4: Size generalisation
GDM outperforms or matches (i.e., is within reported uncertainty of) all originally reported baselines when evaluated across all evaluated graph sizes, despite being trained exclusively on graphs with 15-25 nodes. The differences highlighted for CF and RGC at 200 nodes are negligible relative to the uncertainty, and do not demonstrate a meaningful performance disadvantage. RGC is deterministic and fully observable, so we would expect the deterministic GWM baselines to perform well in this environment. In contrast, GDM achieves substantial improvements in the stochastic OD and SAR environments, while remaining competitive on CF. These are the key environments where a learned model that predicts distributions is useful.
We do not claim that performance is invariant to graph size. Some deterioration is expected due to distribution shift when evaluating on graphs substantially larger than those encountered during training. Nevertheless, GDM retains competitive performance on graphs up to 1000 nodes without retraining, demonstrating its ability to generalise to substantially larger environments.
The additional comparators added during this rebuttal (variants of Vanilla GWM / EA-GWM with GDM’s adjacency module added, copying the previous observation, and the standard Dreamer RSSM) provide additional context. The interpretation in Section 6.1 was revised to be more nuanced in light of these new results.
Dear Authors,
Thank you for the response. I would like to have more details about your response to my first weakness (previous state baseline). I found it is quite hard to understand the revised part in your paper. I would like to have a detailed introduction about: 1. which baselines are added, together with more analysis about the results. Please also introduce the setting of the copy baseline. 2. Please provide more discussion and justification about your claim "This is likely because RGC modifies at most one edge per transition, regardless of graph size." 3. I would also like to know if the code can be provided, especially for the implementation of the added experiment in the rebuttal.
Thank you for your careful review and recognition of the contributions of our work. We welcome the opportunity to clarify these points below. We respectfully note that, while they were listed as Critical Weaknesses (perhaps due to the format of the review form), they mostly concern an additional baseline (W1) and the interpretation of experimental results (W2-W4).
W1: Previous-state baseline
Thank you for this suggestion as it really helps contextualise the GDD values. We have added a baseline which simply copies the previous observation, including the topology, node and graph features, reward, and continuation signal. We have updated Table 1 and Figures 5, 6 in the manuscript to include the new baseline.
This baseline performs poorly in partially observable environments, but achieves strong results in RGC, particularly at larger graph sizes. This is likely because RGC modifies at most one edge per transition, regardless of graph size. As the graph grows, the proportion of unchanged edges increases, while learned models have more opportunities to make prediction errors. When evaluating topology predictions using Jaccard similarity, the copy baseline performs particularly well in OD, and this is the only environment where the copied topology outperforms GDM's topology predictions.
We have also implemented additional GWM variants as baselines which condition adjacency predictions on the previous adjacency, using the same update head as GDM. Please see our response to Reviewer
1txkfor our discussion of these results.W2: Joint kernel in GDD
The joint kernel is the primary component of GDD, and is essential to the theoretical properties of GDD. Unlike an additive-only kernel, it is characteristic, guaranteeing that GDD is zero if and only if the predicted and true distributions are identical. We include the additive terms in the calculation of GDD as it is useful to discriminate between models with similar joint predictions, as discussed in Section 5. This is why each additive MMD term receives only a third of the weighting of the joint term.
To illustrate the importance of the joint term, consider a simple environment with one binary node feature and one binary graph feature. Suppose the true distribution assigns probability 0.5 each to (0,0) and (1,1), while the model assigns probability 0.5 each to (0,1) and (1,0). Both marginal distributions are identical, so MMDadd is exactly zero, despite the predicted joint distribution being entirely incorrect. Using our categorical joint kernel with λn=λg=1, we obtain MMDjoint≈0.632, clearly demonstrating the poor fit of the model, unlike MMDadd.
In the revised version of the paper, we have added an additional row of plots to Figure 5 showing the additive component of GDD only. From the plots, we see that the GDD curves are similar in both shape and conclusion to both the joint terms and the additive terms, but the range of scores for joint MMD is much more compressed than in GDD. For example, in SAR the joint MMD score shows G-RSSM and the GWM models performing very similarly, while including the additive term distinguishes that G-RSSM performs worse at a per-factor level.
W3: Ablation results
The usefulness of individual architectural components (naturally) depends on the environment. βh controls the alignment between deterministic prior and posterior states. Removing this term improves performance in SAR and some CF and RGC settings, suggesting that enforcing alignment is not always beneficial. We didn’t include βh in our hyperparameter search, instead fixing it to 1. These results indicate that it is an impactful hyperparameter which should be tuned for each environment, potentially improving performance further. We have added clarifications to Section 6.3.