- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper looks at PU graph classification, where only a few graphs are labeled as positive and the rest are unlabeled. PEACE checks whether predictions stay consistent under graph perturbations, uses relations between graphs to help assign labels, and then filters out suspicious pseudo-labels using class prototypes. Experiments on several datasets show how it performs, with ablations to check what each part brings.
Critical strengths
- PU graph classification is a meaningful problem, and unreliable pseudo-labels are a real issue in this setting.
- The overall pipeline is clear and easy to follow. The teaser also gives a good overview of the main idea.
- Experiments cover several datasets, with ablations and sensitivity studies to check how the method behaves.
Critical weaknesses
- The method may still introduce errors at several steps. Random edge deletion could remove key structures, and the model might make the same wrong prediction across multiple perturbations. Its performance may also depend on the initial model's ability to separate the classes and whether unlabeled data fits the setting.
- These components rely on perturbations preserving key semantics, similar graphs having similar labels, and class prototypes being representative, but these conditions don't always hold. The first two modules rely on the initial model's predictions, while prototype filtering depends on earlier selections, so errors also can carry over and even get amplified. It's still unclear how much the modules correct each other's mistakes or gain from being combined.
- The gains seem modest, while the method adds extra computation. There's no trade-off study showing whether the extra cost is worth it, and GDE seems to bring limited gains in the ablation results.
- Sec. 3.5 says samples that fail the filtering step aren't used as reliable pseudo-labels, but Eq. (15) still puts the remaining unlabeled samples outside and into the negative-class loss. These two treatments don't seem consistent.
Questions for authors
- Do the three modules help correct each other's mistakes, or can errors still carry over from one stage to the next? Does combining them add much beyond using them separately?
- How much extra computation does PEACE add compared with the baselines? Is the gain worth the extra cost, especially since GDE seems to bring limited gains on some datasets?
- In Eq. (15), why are the remaining unlabeled graphs outside and treated as negatives? Could some still be positive?
If these points are clarified, I'll reconsider my score.