- Rating
- 1
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
This paper studies the adaptation of a node table that is pretrained by link prediction and later fine-tuned for subgraph classification. A subgraph label supervises only the aggregated prediction and does not specify which individual node representations should be updated. Because overlapping subgraphs share the same table rows, they can send conflicting task signals to the model, so training on complete views alone leaves the adaptation of the shared table underdetermined. The authors propose HardLT, which first constructs a fixed reference system from a principal component analysis of the initial table, including a protected set of directions. Within each batch, the method samples several candidate views, each of which applies the same direction mask to every node, and then selects the hardest view according to the mean classification loss of the batch. The model is trained jointly on the complete view and on the selected difficult view to improve classification performance. Experiments adopt the GPEN encoder and report micro F1 on four subgraph classification datasets. Relative to GPEN, HardLT yields absolute micro‑F1 improvements of 0.004 on PPI‑BP, 0.008 on HPO‑Metab and 0.010 on EM‑User, whereas no performance gain is observed on HPO‑Neuro.
Critical strengths
- The problem setting is distinctive. Starting from the shift in supervision granularity, from edge level pretraining to subgraph level labels, the paper argues that a shared node table becomes underdetermined under aggregated labels.
- The globally shared mask is an attractive technical idea. The design aligns the scope of the perturbation, where all nodes share the same direction set, with the shared scope of the adapted parameters. Proposition A.2 rigorously shows that this is not equivalent to independent per node dropout. A global mask preserves the cross row covariance terms, whereas independent row masks remove the interactions between different rows.
Critical weaknesses
-
According to the results in Table 1, HardLT does not achieve a significant improvement in micro F1 over the baselines.
-
The writing quality is poor. The entire paper reads in a very stiff and awkward manner. The research motivation together with the problem introduction are not clearly conveyed. The related work section is far too brief. For example, the sentence "WLKS and ISNN develop further structural representations" does not explain how these methods work or why they are able to develop further structural representations. The section also fails to discuss other works on pretraining adaptation. In addition, the comparison table that appears in the related work section has no table caption. The figures need more annotations to be self explanatory. Figure 1 contains a large number of formulas without any explanation of what each formula does. The text inside Figure 1 should also use a uniform font size. The problem formulation in Section 3 should be a concise, symbol based formalization.
Questions for authors
- Why not use node representations generated by pretraining on node classification or other tasks for subgraph prediction? What advantage do node representations derived from link prediction specifically offer? Are there any relevant applications for subgraph classification models pre-trained via link prediction?
- Why should the partial view discard the PCA residual entirely? If downstream adaptation produces new directions outside the initial PCA subspace, does existing method hinder that adaptation?
- Does the method generalize to subgraph encoders other than GPEN?