- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes ITXGNN, a self-interpretable GNN designed to improve explanation stability across graph instances. It defines stability through intra-group consistency and inter-group discrimination, and combines subgraph extraction, learnable clustering, and prototype-based representation learning with an information-theoretic objective. Experiments demonstrate improved stability metrics while maintaining competitive predictive performance.
Critical strengths
S1. The paper addresses an important problem by explicitly considering both intra-class explanation consistency and inter-class discrimination. S2. ITXGNN achieves substantial improvements in explanation stability across synthetic and molecular graph benchmarks. S3. The paper provides theoretical analysis, ablation studies, and qualitative examples to support its methodology.
Critical weaknesses
W1. Definition 1 uses expected pairwise explanation distances, whereas the molecular experiments compute FID between randomly divided subsets, which does not directly measure within-class explanation variability. W2. Maximizing mutual information between prototypes and clusters does not necessarily guarantee structural consistency among extracted subgraphs, and Theorem 1 only establishes a bound in the embedding space. W3. The experiments lack systematic evaluation of explanation faithfulness and ground-truth overlap, making it difficult to determine whether more stable explanations are also more accurate. W4. The ablation study is limited to BA-2Motif, and the improvement over frozen clustering is small relative to the reported standard deviations.
Questions for authors
Q1. In Section 6.1, why is FID between two random subsets used to approximate the intra-group dispersion in Definition 1? Since both subsets come from the same distribution, their FID can approach zero even when individual explanations differ substantially. Could the authors report direct pairwise explanation distances? Q2. How does the objective in Equation 3 ensure that extracted subgraphs are structurally stable rather than merely producing well-separated embedding clusters? Can the authors empirically verify the relationship between prototype separation and subgraph-level stability? Q3. Could the authors report explanation F1/Jaccard against ground-truth motifs and faithfulness metrics under matched explanation-size budgets? This would clarify whether the stability improvements correspond to identifying more relevant subgraphs. Q4. How are the cluster assignment probabilities (q_{ik}) learned and inferred for unseen graphs? Are prototypes recomputed from batch embeddings or directly optimized using the prototype learning rate reported in Appendix D? Q5. Could the authors extend Table 4 to molecular datasets and compare against simpler class-conditioned contrastive or prototype-based regularization using the same backbone?
2 comments
Response to Reviewer 8qHm (2/2)
Q4. Learning . The assignments are free parameters for the training graphs only, , optimized jointly with the model under the full objective. They are initialized from the training labels: one-hot plus small noise when , and round-robin over a class's sub-prototypes when , so the within-class split is learned. Validation and test graphs never enter .
Prototypes are not directly optimized. At each step they are recomputed as the -weighted mean of the mini-batch's subgraph embeddings, (Sec. 4.2), so gradients flow to both and the encoder.
For unseen graphs is not used. After training, prototypes are computed once over the full training set with the learned . A test graph is embedded and assigned by its similarity to these prototypes (softmax for soft, argmax for hard). No test-time optimization or test information is used. In Appendix D the "prototype" learning rate applies to the prototype layer's other parameters (the prototype-to-class matrix for , and the LayerNorm before cosine similarity), not to the prototypes. We will relabel it.
Q5. We thank the reviewer for the suggestion and think it is an excellent addition to support claims made in the paper. We extend the existing ablations done for BA-2Motif on MUTAG. We also add 2 new baselines; a supervised contrastive loss and a prototype regularization baseline (using a center loss) with the same backbone for both MUTAG and BA-2Motif (Tables R4 and R5).
On BA-2Motif, both baselines reach perfect accuracy, but their explanations collapse to near the whole graph (intra-class nGED 0.632). The IsoRate gap drops from 0.895 to 0.000, and the nGED ratio rises from 0.109 to 0.971. On MUTAG, ITXGNN's explanations are far more consistent in both spaces: the within-/between-class ratio is 0.412 vs 0.783–0.795 (GIN) and 0.644 vs 0.882–0.906 (ECFP). Its accuracy is equal or higher (0.937 vs 0.884–0.916). On BA-2Motif (K = C), the labels already give the right clustering, so learning it adds little and the gap to frozen clustering is small. On MUTAG (K = 4) the gap is clearer: 0.500 vs 0.412 (GIN), lower on 4/5 seeds.
Class labels alone are therefore enough for accurate prediction, but not for stable explanations. Stability comes from the clustering objective, I(Ĉ;P), on both a synthetic and a molecular dataset. Full results, with more seeds and datasets, will be included in the final version.
Response to Reviewer 8qHm (1/2)
We would like to thank the reviewer for taking the time and effort to read and understand our work, we appreciate the constructive feedback.
Q1. We agree, and we now report direct pairwise explanation distances. For all methods on all four molecular datasets, we compute the average within-class and between-class pairwise distances in ECFP and GIN embeddings and report their ratio (Table R1). ITXGNN has the lowest ratio on every dataset in both spaces: 0.43–0.84, vs 0.70–1.05 for the baselines. Its same-class explanations are therefore closer to one another than to other-class explanations under the quantity Definition 1 defines. FID is kept as a supplementary distribution-level analysis which we will move to the appendix.
Q2. The objective acts on embeddings and does not by itself guarantee structural stability. Embedding stability is nevertheless the right target, for two reasons. First, structural stability cannot be optimized directly: isomorphism and edit distance are discrete and non-differentiable, whereas agreement in embedding space can be trained end to end. Second, the embedding is what the model predicts from so explanations that agree in embedding space mean that same-class graphs are classified on the same evidence. Because the extractor is trained through the same objective, the simplest way to make a cluster's embeddings agree is to select the shared structure; mapping structurally different subgraphs to the same point would require the encoder to discard their differences. Empirically, this is what happens. On BA-2Motif, the IsoRate of 0.970 shows that embedding clusters coincide with isomorphic subgraphs. To verify the relationship directly, we have conducted a new experiment; where we perturb the learned explanations of a trained model by adding or removing nodes or replacing them with a different subgraph (Table R7). The distance to the class centroid grows with the structural deviation, from 0 for the learned explanation to 0.066 after adding five nodes, 0.210 after removing two, and 0.502 for a different subgraph, and the cross-entropy loss increases accordingly.
Q3. We appreciate this suggestion and have added this experiment. We note that ITXGNN has the highest mean Jaccard with the ground-truth motif on all five datasets, at matched explanation size (Table R2). The margin is wide on BA-2Motif (0.994 vs at most 0.640) and Benzene (0.803 vs at most 0.545). Together with Table R1, this suggests that the method with the most stable explanations is also the most accurate with respect to the ground truth. The stability gains therefore do not come at the expense of correctness.
Faithfulness (Table R6). ITXGNN's Fid− is at most 0.003 on all five datasets: its explanation alone reproduces the prediction, as expected for a self-interpretable model. Its Fid+ is highest on BA-2Motif, SPMotif and Fluoride-C. On Benzene and Alkane-C., SubgraphX scores higher (0.428 vs 0.396; 0.389 vs 0.370) but removes between 2 and 5× more of the graph (66–68% of nodes vs 13–33%), and removing more of the graph tends to change the prediction more. Ground-truth overlap is the more direct test of relevance, and there ITXGNN is best on all five datasets (Table R2). Fidelity is reported at each method's own size, shown in Table R6(c).