- Rating
- 4
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper introduces the Temporal Simplicial State Space Model (TSSSM) utilising higher-order interactions between nodes to find evolving simplicial embeddings. This is built upon a foundation theory of Temporal Simpicial Complexes showing these satisfy an WL-like test for expressibility. Notationally, this is challenging to follow with many concepts to keep track of, but the theory is well-explaind to justify the TSSSM. The most innovative part of the work is to formalise the problem as a Embedding Reconstruction Problem, which generalises other topological reconstruction problems.
The TSSSM shows competitive performance among other methods designed to use higher-order interaction information such as FastHeP and CAT-Walk. While no method strictly dominates the others, they provided a marked improvement over clique-expansion methods especially for datasets where higher-order interactions are richest. The benefit of TSSSM over FastHeP and CAT-Walk is it's improvement in run-time with a much lower time per epoch.
The paper describes the simplest version of this admittedly complex model incorporating historical states through an additive weighting and single-layer linear aggregation. This paper provides the starting point for further investigation into the promising TSSSM.
Critical strengths
The paper does an excellent job of explaining the theory necessary for TSSSM (Sections 3-5). As someone new to the higher-order temporal interaction networks, I felt this work walked me through the key ideas to appreciate the purpose of these theorems. Unfortunately, the ICLR reviewing schedule means I do not have the time to fully work through proofs to my desired level, but this is something I plan to return to in future.
TSSSM shows competitive performance among other methods designed to use higher-order interaction information such as FastHeP and CAT-Walk, but at a much improved runtime per epoch. Given the paper focuses on the simplest version of TSSSM using additive weighting and single-layer aggregation, it provides an excellent foundation for further improvements for specific higher-order networks.
Critical weaknesses
Section 6 (Model Architecture) had a few vague statements which failed to fully explain the computational pipeline, for instance, simplex neighbour selection and the temporal encoder. These are listed as questions for the authors below. It noticeably lacked the level of detail seen in the rest of the theoretical work.
Section 7 (Numerical Experiments) also lacked details in places. For example, it is not clear how the TSSSM embedding output is used to predict higher-order links in the negative sampling experiment. Similarly, this is even less clear for the dynamic closure prediction which is relegated to a short paragraph. This feels a result of lack of space in an otherwise incredibly dense paper, rather than these details being unavailable.
Questions for authors
- How are neighbouring simplices chosen as part of the sampling? Is this done uniformly over all possible neighbours, or is there a preference for simplices in ? Changes in sampling here could offer improvements to the TSSSM training.
- How is the temporal encoder defined in the decoder subsection of the Model Architecture? It was not clear what role this plays in the larger training. This could also help my understanding of the Numerical Experiments and the task-specific learnable transformation .
3 comments
Thank you for your rebuttals to me and the other reviewers. I will continue to follow discussions elsewhere and I will keep my positive rating.
We sincerely appreciate the reviewer’s continued support and positive assessment. Thank you for your time, thoughtful feedback, and constructive engagement through the review process.
We thank the reviewer for their positive assessment of our work and appreciate the suggestions made regarding the explanations in Sections 6 and 7. We will incorporate these changes into the main manuscript to improve the clarity and readability of these sections.
Response to W1 :
We agree with the reviewer's assessment and will integrate detailed explanations for simplex neighbor selection, the temporal encoder, and other additional details into the main manuscript.
Response to W2 :
We appreciate the suggestion pointing out the lack of clarity in these parts and will add a detailed explanation for them.
For a query simplex (σ,t)—which may come from the link prediction task asking the model if simplex σ will be observed at some future time t—we use Eq. 14 to generate its embedding for time t. This uses the available state for simplex σ, the elapsed time Δt between the last update of σ and time t, and the states associated with its neighbors. We then apply a linear transformation to produce a scalar score from this embedding, and the model is trained to output higher scores for queries associated with positive samples and lower scores for those associated with negative samples. Because the embedding requires states from σ and its neighbors, and negative samples are generated with partially random combinations of nodes, we can encounter a simplex σ in the query that has never been observed before. For these simplices, the model provides a default 0 state vector and a very high Δt≈1011, along with the states of its neighbors if they have been observed. In this case, the embeddings are primarily derived from the components aggregated from the neighbors and the temporal embedding.
Although this might give the impression that a default 0 or a very high Δt signals to the model that the sample is negative, this is ruled out in the strong inductive and inductive settings. In those settings, positive samples also include simplices that were not observed during training and thus have a 0 state vector until their first encounter in the test split.
Similarly, for closure prediction at time ti and for a candidate triplet σ= {a,b,c}, we calculate the score for time ti+1 using the same ingredients: the state at ti, the elapsed time Δt=ti+1−ti, and the neighbors' states. A higher score indicates the closure or formation of a closed triangle, whereas a lower score indicates an open triangle or hole.
Response to Q1:
For neighbor sampling, we implemented two policies: recency and uniform. Recency-based sampling selects the N most recent neighbors, whereas uniform sampling draws uniformly from all neighbors. In our numerical experiments, we present results using recency-based sampling. We preferred this approach over uniform random sampling because most standard temporal graph networks adopt it. We will add this detail more clearly to the main manuscript.
Response to Q2:
Our work uses the standard Time2Vec temporal encoder with logarithmic scaling of the input x to form an embedding xt of the form xt=Time2Vec(log(1+x)). This encoder primarily aids the model in generating embeddings for a given time t.
Specifically, given a simplex that was last updated at ti and an embedding that is required for time t>ti, the model uses the simplex state from time ti, the elapsed time Δt=t−ti, and the neighbor states of the simplex to generate the embedding for time t.
Using this temporal embedding, the states of the simplex and its neighbors, and a transformation matrix W, the model generates a scalar score for predictive tasks or a vector score if multi-class classification is required.
Finally, we thank the reviewer again for their efforts in providing this review, and we hope the explanation helps clarify their concerns. We would be happy to respond to any additional concerns or queries they may have regarding the manuscript or the submitted response.