- Rating
- 2(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces NOGI, a framework for learning network structure and continuous-time dynamics together from observed trajectories of the studied system. NOGI combines an explicitly learned sparse adjacency matrix with a graph-conditioned Neural ODE to model system dynamics. Experiments on several synthetic dynamical systems and the Netsim benchmark demonstate strong structure-recovery performance, including under sparse and irregular observations.
Critical strengths
-
The joint learning of network structure and continuous-time dynamics is well motivated and potentially useful for systems with irregular or incomplete observations. But this idea is not completely new, e.g., GNeuralFlow (NeurIPS 2024) also jointly learns graph structure and continuous-time dynamics from irregularly sampled time series.
-
The evaluation in the paper covers multiple dynamical systems, graph topologies, network sizes, and missing-data regimes. The reported AUROC and AUPRC results are generally strong, and the paper investigates challenging observation settings as well.
Critical weaknesses
-
Although the experiments conducted in the paper are broad, the baseline comparisons do not establish comprehensive coverage of recent structural-inference methods. Comparisons with approaches such as GNeuralFlow, iSIDG, SIDEC would help clarify NOGI’s relative contribution.
-
The performance of NOGI is not always superior across all settings, so the scope of the paper’s empirical superiority claims should be carefully qualified.
-
It is difficult to isolate the benefits of the continuous-time formulation and joint graph-dynamics learning without sufficiently targeted comparisons or ablations.
Questions for authors
Related to the identified weaknesses:
-
Can the authors compare NOGI with additional structural-inference methods, ideally on at least one shared benchmark with consistent data splits and AUROC/AUPRC metrics?
-
Which components of NOGI contribute most to its performance, and how do the authors disentangle their effects?
2 comments
Thank you for the response which (partially) addresses the weaknesses from my review. I also look at the other reviews, author responses and discussions. I can raise my score a bit, but still feel that the work does not meet the standards of ICLR conferences.
Response to Reviewer V9ur
W1/Q1:
We compare NOGI with iSIDG and SIDEC on four datasets from the public StructInfer benchmark. Baseline numbers are taken from Table 1 of the SIDEC paper, and NOGI follows the same protocol: the official data splits, AUROC over the full adjacency matrix, and an average over 10 runs. NOGI outperforms iSIDG on all four datasets, outperforms SIDEC on VN_SP_50 and VN_SP_100, and is slightly behind SIDEC on VN_NS_50 and VN_NS_100.
W2:
We would like to clarify that our claims are explicitly scoped to the evaluated settings: we report best or jointly best structure recovery in 30 of 32 comparisons, explicitly identify the exceptions in §3.2, and discuss settings where NOGI does not outperform competing methods in §§3.3–3.4.
W3/Q2:
We ablate one component at a time on Spring and Kuramoto (ER, N=100) under observation interval K, with all other settings fixed within each column. Each cell reports AUPRC over three seeds:
The benefit of continuous-time modeling appears at large intervals: over a long interval, influence spreads across multiple hops, which a discrete-time model can only explain with spurious direct edges, whereas NOGI's graph describes only instantaneous interactions and lets the integration produce the multi-hop effects. For the other components, deterministic graph learning contributes most, pairwise message passing is essential on Kuramoto, and sparsity regularization gives a further gain. We have added this ablation study to the revised paper. As for joint graph-dynamics learning, it is the task setting shared by NRI, AIDD, NGM, and SCOTCH rather than a design choice of NOGI, and Table 1 already contrasts this setting with methods that infer the graph without a dynamics model (MI, PC).