- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper studies graph robustness against joint lable-structure noise under node classification setting. Specifically, the authors notice that if both label and structure are noisy, feature can provide clean information. So, they firstly construct anchors from feature, then enhance the similarity between two end-nodes of one edge if the nodes belong to the same anchor, and also align the supervised gradient with that of high-confidence unlabeled nodes.
Critical strengths
None.
Critical weaknesses
-
Motivation. This paper mainly claims that previous models focus on either label noise or structure noise, but none of them solves the both, so the authors did. It sounds like a A+B story, not very interesting. Among label, structure and feature, there are totally 3 binary combinations, and 1 ternary combination. Therefore, there could be 4 such papers. Also, the proposed technique mainly relies on clean feature, but if feature is also noisy, also a common setting, this method will fail.
-
Method. The key of DEFENCE is to construct a high-quality set of anchors, Eq. (1) and (2). This construction is composed by one-layer MLP, K-Means, and label alignment. I concern if the one-layer MLP + K-Means is strong enough to build anchors. Given the lables are noisy, I also concern if the label alignment and hard anchor assigment can improve the anchors.
-
Theory. In theory, the authors attempt to prove if is better than random guess, will correct more on the nodes with wrong labels.
- The conclusion is straight. If we assume is better than random guess, then contains some ground-truth label information. Therefore, if one node is given an incorrect class, it deviates more from , and naturally has a larger gradient if we use
- The reason for Eq. (4) is to reduce the drift induced by corrupted labels and noisy propagation. So, the theory needs to prove the gradient alignment is better than no alignment.
- The assumption is better than random guess is not always true, especially for one-layer MLP + K-Means.
- Experiments. The authors also need to show that with the increase of noise level, the proposed DEFENCE performance decreases much slower than baselines, which indicates the method is robust.
Questions for authors
Please check the weaknesses part.
2 comments
W3. Anchor reliability and Theorem.
Our analysis explains how imperfect but informative anchors support robust learning through two distinct mechanisms.
Theorem 1 — Cleaner pairwise supervision. Theorem 1 quantifies how better-than-random hard assignments improve positive- and negative-pair purity in L_cont. This reduces cross-class positive pairs and same-class negative pairs, limiting erroneous attraction and repulsion between node representations. The resulting cleaner contrastive supervision reduces the influence of corrupted graph structure on representation learning.
Theorem 2 — Selective regularization. Under the classwise better-than-random anchor assumption, Theorem 2 shows that L_align applies stronger output-level correction when predictions follow incorrect labels than when they follow clean labels. As shown in our response to W2, anchors outperform model predictions in the early stage of training. At this stage, L_align guides predictions toward a more accurate feature-derived reference. Its stronger correction for predictions following incorrect labels opposes noisy-label fitting, while its weaker correction for predictions following clean labels limits interference with reliable supervision, supporting robust learning under joint noise.
Empirical support. We evaluate whether the constructed anchors satisfy the informativeness conditions required by Theorems 1 and 2 and provide reliable pairwise supervision under joint noise. Hard-anchor accuracy exceeds the corresponding chance level in all 15 evaluated settings (Table 1). For Theorem 2, the minimum classwise mean true-class anchor probability exceeds (1/C) in all 10 evaluated settings (Table 2). Anchor filtering also improves both positive- and negative-pair purity on all three datasets (Table 3). These results support the anchor-informativeness premise and directly corroborate the pair-filtering benefit.
Table 1
| Dataset | (0.1, 0.1) | (0.1, 0.2) | (0.1, 0.5) | (0.2, 0.1) | (0.5, 0.1) | Random guessing (1/C, %) |
|---|---|---|---|---|---|---|
| Cora | 59.00 | 57.59 | 44.24 | 61.64 | 43.42 | 14.29 |
| PubMed | 71.06 | 71.56 | 46.04 | 72.09 | 73.59 | 33.33 |
| Citeseer | 77.59 | 73.52 | 53.90 | 76.60 | 69.79 | 16.67 |
Table 2
| Dataset | (Label noise, Structure noise) | Minimum classwise mean true-class anchor probability (%) | Random guessing (1/C, %) |
|---|---|---|---|
| PubMed | (0.1, 0.1) | 36.61 | 33.33 |
| (0.1, 0.2) | 38.62 | 33.33 | |
| (0.1, 0.5) | 37.98 | 33.33 | |
| (0.2, 0.1) | 37.29 | 33.33 | |
| (0.5, 0.1) | 33.62 | 33.33 | |
| Citeseer | (0.1, 0.1) | 33.43 | 16.67 |
| (0.1, 0.2) | 35.35 | 16.67 | |
| (0.1, 0.5) | 41.49 | 16.67 | |
| (0.2, 0.1) | 33.44 | 16.67 | |
| (0.5, 0.1) | 18.80 | 16.67 |
Table 3
| Dataset | Positive purity (before → after) | Negative purity (before → after) |
|---|---|---|
| Cora | 64.76 → 80.10 | 82.27 → 87.57 |
| PubMed | 68.75 → 79.01 | 64.37 → 74.77 |
| Citeseer | 74.92 → 93.06 | 83.04 → 90.95 |
We added this analysis in Appendix A9.
W4. Performance degradation as noise levels increase
Our existing experiments evaluate noise rates of 0.1 and 0.2 in Table 1 and extend the range to 0.5 in Appendix A.5 (Table 5). We quantify degradation by computing the accuracy drop from 0.1 to 0.5 while keeping the other noise rate fixed at 0.1.
Averaged over all four datasets, DeFence’s accuracy drops by 18.93 percentage points under increasing label noise and 4.40 points under increasing structure noise, compared with 24.75 and 6.58 points for GDF, respectively. For increasing label noise on Cora and Citeseer, the mean drop is 14.30 points for DeFence versus 23.50 points for RNCGLN; the other datasets are excluded from this comparison because RNCGLN encounters out-of-memory errors.
The degradation trend depends on the dataset, baseline, and noise source. RNCGLN has smaller structure-noise drops on the two shared datasets, while DeFence achieves higher accuracy at the high-noise endpoint.
We have added these comparisons of accuracy drops to Section 4.2 of the revised manuscript.
We thank the reviewer for the detailed comments. We clarify the contribution and provide additional evidence below. We have also incorporated the corresponding revisions into the manuscript, with all changes highlighted in blue.
W1. Novel research problem
Motivation and methodological contribution. The joint label–structure noise problem has already been studied by RNCGLN and GDF. We already discussed both methods in the Related Work section and included them in our experimental comparisons. Our contribution is an anchor-guided learning strategy that addresses the mutual reinforcement of label and structure errors: corrupted edges distort neighborhood aggregation, while noisy supervision reinforces the resulting representation errors.
DeFence addresses this interaction through a periodically fixed anchor reference constructed from pre-propagation feature embeddings. The reference guides contrastive pair selection and posterior regularization. Under the respective assumptions of Theorems 1 and 2, even anchors that are only better than random increase positive- and negative-pair purity and induce stronger expected output-level correction for predictions following corrupted labels. These effects support robust learning by providing cleaner pairwise supervision and selectively regularizing predictions driven by noisy labels. Our additional anchor-quality and pair-purity measurements provide empirical support for this mechanism under joint noise (see the answers for W2 and W3).
Scope and future work. This work focuses on joint label and structure corruption; feature corruption lies outside the evaluated scope. Extending DeFence to simultaneous feature, label, and structure corruption is an important direction for future work.
We have clarified our methodological contribution in the Introduction by explaining how periodically fixed anchors from pre-propagation feature embeddings guide contrastive pair selection and posterior regularization under joint label-structure noise. We have also highlighted robustness to simultaneous feature, label, and structure corruption as an important direction for future work in the Conclusion Section.
W2. Anchor reliability through training
Anchor reliability throughout training. To directly assess the anchors produced by the one-layer encoder and K-means, we compare anchor and model accuracy at 10%, 30%, and 100% of training across three datasets and two joint-noise settings.
Anchors are more accurate than model predictions early in training in all six settings. At 10% of training, anchor accuracy exceeds the corresponding model performance in every setting. Anchors remain more accurate in four of six settings at 30%, while model predictions surpass anchors in all six settings by the end of training. This pattern supports the intended role of anchors as informative early guidance, with final predictions exceeding the accuracy of that guidance.
We added this analysis in Appendix A9.