- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2(+1)
Read review
Paper summary
The paper proposes AD-DHGNN, a dynamic hypergraph neural network that adaptively determines both the number of hyperedges and the number of nodes within each hyperedge during encoding.
It combines a PageRank-based graph encoder with a Gaussian mixture–based candidate generation pipeline and adaptive structural controllers.
Experiments compare the proposed method against several hypergraph neural network baselines on seven node-classification benchmarks.
Critical strengths
-
S1. The key challenge, selecting informative hyperedges, is an important and practical research question for the use cases of hypergraph neural networks.
-
S2. Adaptive hyperedge selection specialized to each dataset is reasonable and intuitive.
Critical weaknesses
-
W1. Methodological novelty. The proposed framework combines established techniques, including APPNP, Gaussian mixture modeling, and spectral knee detection. Although their integration for joint hyperedge count and cardinality control is potentially useful, the methodological advance beyond this combination remains unclear. The authors should clarify which design elements introduce new insights specific to hypergraph construction and how they differ from existing adaptive structure-learning approaches.
-
W2. Baseline coverage. Although the experiments include recent hypergraph methods, several relevant comparisons are missing. For example, FDHNN (2026) is discussed in the related work but is not evaluated. Moreover, because the evaluated datasets are originally graphs and the proposed method uses an APPNP backbone, comparisons with competitive graph neural networks would help establish the benefits of hypergraph reconstruction. The authors should expand the baseline coverage or explain the exclusions.
-
W3. Relationship to homophily. The method constructs hyperedges from representation similarity, making its relationship to homophily particularly relevant. However, the paper does not systematically examine whether the reconstructed hyperedges exhibit greater label homophily or how their homophily relates to classification performance. Evaluating datasets with varying levels of homophily would also help clarify whether the method remains effective when similar or connected nodes have different labels.
Questions for authors
See Weakness
5 comments
Response to W2. Thank you for the reviewer’s comment. We evaluated FDHNN on all seven real-world datasets. We also compared AD-DHGNN with validation-tuned GCN, GAT, and APPNP models using the same dataset splits. All experiments were conducted on an RTX A800 GPU with 80 GB of memory. Table 1 shows the baseline hyperparameter settings.
Table 1. Baseline hyperparameter settings.
| Method | Hyperparameter settings |
|---|---|
| GCN | Hidden dimension: {64, 128, 256}. Layers: {2, 3}. Dropout: {0, 0.3, 0.5, 0.7}. Learning rate: {0.001, 0.003, 0.01}. Weight decay: {0, 0.0005, 0.005}. |
| GAT | Hidden dimension, dropout, learning rate, and weight decay use the GCN ranges. Attention heads: {2, 4, 8}. Attention dropout: {0, 0.3, 0.5, 0.7}. |
| APPNP | Hidden dimension, dropout, learning rate, and weight decay use the GCN ranges. Propagation steps K: {5, 10, 20}. Teleport probability α: {0.05, 0.1, 0.2}. |
| FDHNN | Hidden dimension: 128. Number of edges: {100, 150, 200}. Minimum number of edges: {10, 20, 30}. k: 10. Learning rate: 0.001. Weight decay: 0. |
Table 2 reports the results. AD-DHGNN outperforms FDHNN on all five datasets where FDHNN completed its run. FDHNN controls hyperedge cardinality and count through preset hyperparameters, whereas AD-DHGNN adapts both using data-dependent structural information. This difference may partly explain AD-DHGNN’s stronger classification performance.
CiteSeer is the only dataset on which AD-DHGNN does not exceed GAT. CiteSeer has relatively sparse connections and high-dimensional features. These dataset characteristics may make node–anchor similarity estimates less stable and contribute to the smaller result on CiteSeer.
Table 2. Classification performance (%). The first six datasets use accuracy, and Yelp uses Micro-F1. Results are mean ± standard deviation.
| Method | Cora | CiteSeer | PubMed | Physics | Amazon Computers | ogbn-arxiv | Yelp |
|---|---|---|---|---|---|---|---|
| GCN | 81.56 ± 0.61 | 71.86 ± 0.28 | 77.94 ± 0.46 | 96.70 ± 0.07 | 69.22 ± 0.78 | 65.69 ± 0.22 | 22.09 ± 3.26 |
| GAT | 81.46 ± 0.50 | 71.50 ± 0.76 | 77.48 ± 0.47 | 96.45 ± 0.05 | 71.85 ± 3.63 | 65.36 ± 0.07 | 20.37 ± 3.05 |
| APPNP | 82.72 ± 0.41 | 71.10 ± 0.55 | 78.42 ± 0.21 | 96.60 ± 0.06 | 69.68 ± 0.52 | 65.55 ± 0.24 | 21.52 ± 1.88 |
| FDHNN | 79.40 ± 0.59 | 64.36 ± 1.38 | 76.94 ± 1.05 | 96.30 ± 0.78 | 71.22 ± 0.86 | OOM | OOM |
| TDHNN | 82.77 ± 0.32 | 65.81 ± 1.23 | 78.13 ± 0.37 | 96.52 ± 0.18 | 69.97 ± 0.93 | 52.77 ± 0.82 | 32.20 ± 1.15 |
| AD-DHGNN | 83.57 ± 0.13 | 71.22 ± 0.24 | 80.14 ± 0.17 | 97.26 ± 0.11 | 80.72 ± 0.71 | 70.35 ± 0.23 | 50.83 ± 0.17 |
Response to W3. Thank you for raising this question. We measure hyperedge label homophily as the proportion of same-label node pairs among all node pairs within the evaluated hyperedges:
\frac{ \sum_{e\in\mathcal E} \sum_{i < j,\\,v_i,v_j\in e}\mathbf{1}[y_i=y_j] }{ \sum_{e\in\mathcal E}\binom{|e|}{2} }.$$ Here, $\mathcal E$ is the evaluated hyperedge set and $y_i$ is the label of node $v_i$. Labels are used only for post-inference analysis, not for hyperedge construction. Table 1 compares the label homophily and classification accuracy obtained by using candidate hyperedges directly with those obtained after adaptive dual-control reconstruction. The reconstructed hyperedges have higher label homophily, and the model achieves higher classification accuracy. **Table 1. Effect of adaptive dual-control reconstruction on hyperedge label homophily and classification accuracy on Cora.** | Hyperedge type | Label homophily (%) | ACC (%) | |---|---:|---:| | Before Reconstructed | 31.30 ± 2.11 | 81.67 ± 1.46 | | Reconstructed Hyperedges | **86.50 ± 0.96** | **83.57 ± 0.13** | To compare performance across different homophily levels, we use **original-graph edge homophily** as the proportion of edges connecting same-label nodes in the undirected input graph, excluding self-loops: $$h_{\mathrm{graph}} = \frac{ \sum_{\\{i,j\\}\in E,\\,i\ne j} \mathbf{1}[y_i=y_j] }{ \left|\\{\\{i,j\\}\in E \mid i\ne j\\}\right| }.$$ Here, $E$ is the set of undirected edges in the input graph, $y_i$ is the label of node $i$, $i \ne j$ excludes self-loops, and $\mathbf{1}[y_i=y_j]$ equals 1 if nodes $i$ and $j$ share the same label and 0 otherwise. Table 2 presents the corresponding results. The original-graph edge homophily of Roman-empire, ogbn-arxiv, and Physics is 4.69%, 65.42%, and 93.14%, respectively. AD-DHGNN exceeds GCN in test accuracy by 7.93, 4.66, and 0.56 percentage points on these datasets. The results show classification gains in the evaluated low, medium, and high-homophily settings. AD-DHGNN achieves gains at all three homophily levels, with the largest improvement over GCN on the low-homophily Roman-empire dataset. **Table 2. Classification accuracy on datasets with different levels of original-graph edge homophily.** | Dataset | Original-graph edge homophily (%) | GCN (%) | AD-DHGNN (%) | |---|---:|---:|---:| | Roman-empire | 4.69 (low) | 46.63 ± 0.17 | **54.56 ± 0.60** | | ogbn-arxiv | 65.42 (medium) | 65.69 ± 0.22 | **70.35 ± 0.23** | | Physics | 93.14 (high) | 96.70 ± 0.07 | **97.26 ± 0.11** |
Response to W1. Thank you for the reviewer’s suggestion. Existing dynamic hypergraph methods update hyperedge based on node representations, and some also adjust the number of hyperedges. Our design further addresses two decisions in hypergraph construction.
First, different hyperedges may require different cardinality. A dense local region may support a larger hyperedge cardinality, whereas a small local group should not be forced to expand. We therefore use the size of each candidate’s local region to set its cardinality upper bound, then select members according to the strength of their association with that candidate. The local region determines how many nodes the candidate can contain; it does not directly determine which nodes it must contain.
Second, the model must determine both how many hyperedges to retain and which ones to keep. Similarity among candidates helps identify repeated structure, but using similarity alone may remove candidates that cover different nodes or regions. We therefore combine structural redundancy with complementary coverage to guide both the retained count and candidate selection.
Together, these two designs limit the overexpansion of individual hyperedges and reduce duplication among candidates. APPNP provides node representations informed by the original graph, the GMM estimates candidate membership, and spectral knee detection informs the number of hyperedges to retain.
The proposed method focuses on assigning candidate-specific size limits, rather than using k-means or k-nearest neighbours, and selecting the final hyperedges based on both structural redundancy and complementary coverage. As shown in Table 1, AD-DHGNN produces a more balanced hyperedge count and cardinality range than the compared methods, with substantially lower structural redundancy.
Table 1. Structural properties of the constructed hypergraphs.