- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies negative-free graph-text and graph-text-image representation learning for transfer across text-attributed graphs. It proposes LeGramJEPA, which replaces pairwise cross-modal prediction with a per-anchor Gram-determinant volume loss and uses SIGReg to constrain each modality’s embedding distribution. The method is evaluated on zero-shot node classification and link prediction, plus linear probing in a three-modality setting.
Critical strengths
-
The paper provides a clear computational formulation with a meaningful efficiency advantage.
-
The empirical evaluation demonstrates that the negative-free objective is viable in several transfer settings.
-
The figures are clear and helpful to understand the framework.
Critical weaknesses
-
Minimizing the Gram determinant only enforces linear dependence, not full alignment across modalities.
-
The three-modality experiments rely primarily on downstream linear probing, without directly measuring whether all modalities are jointly aligned. Cross-modal retrieval experiments or embedding alignment diagnostics would better substantiate the proposed objective.
-
Appendix D.1 reports the best-performing scoring direction separately for each target dataset, potentially using target test labels for model selection. This undermines the strict zero-shot setting and may introduce an unfair advantage over GraphCLIP.
-
LeGramJEPA underperforms GraphCLIP on four of seven zero-shot node classification datasets. Moreover, the three-modality model fails to outperform the best two-modality variant, raising concerns about the effectiveness of the proposed multimodal extension.
-
The efficiency claims are supported primarily by loss-only benchmarks on synthetic embeddings rather than end-to-end pretraining experiments. Furthermore, the proposed objective is slower than InfoNCE for batch sizes below approximately 2,554, making its practical efficiency advantages unclear.
Questions for authors
- How does the implementation or optimization dynamics rule out rank-deficient but non-aligned multimodal solutions of the form while remains independent, for which every three-modality determinant in Equation (6) is zero?
Rebuttal
We thank the reviewer for the careful reading. We address the weaknesses below.
W2. No direct measure of three modality alignment.
MM-Graph evaluates Ele-Fashion and Goodreads-NC only with supervised GNNs trained on each target. A frozen-encoder probe on the same splits allows us to compare the pretrained model next to the supervised results (Table 3; App. D.2). We believe that the node classification and link prediction results already show that alignment is learned via the volumetric term.
W3. Scoring direction chosen per target dataset.
Thank you for this question.We will clarify App. D.1. A single scoring direction, [cos(z_g, h_t(z_t))], is used for all seven target datasets; it is not chosen per dataset. We will add further clarification in App. D.1 to make the zero-shot scoring clear.
W4. Performance relative to GraphCLIP, and three modalities.
The focus of this paper is to demonstrate that a negative-free self-supervised objective is competitive with the contrastive methods in graph learning. Under three modalities, the focus here is to demonstrate that a model trained with simpler k volumetric alignment terms instead of k(k-1) still outperforms both GraphCLIP across each modality pair.
W5. Efficiency Claims
Thank you for raising this point, the benchmark in App. H mainly focuses on the loss with synthetic embeddings, therefore following your suggestions we have included an extra experiment, instead we now include the timed forward pass and peak memory inside a full pretraining run with the encoders. We compare against GraphCLIP's loss, symmetric InfoNCE, and the cross pairwise objective (Eq. 15).