- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
The paper studies whether pretrained brain foundation models capture information relevant to individual cognitive differences. The authors first show that the foundation models fall short and even worse than FC baselines, then they propose a pretraining objective that prioritize high-variance signals, along with an imporved FC baseline with Tucker decomposition.
Critical strengths
- The research question is important. The paper shows the foundation model may not perform as they are expected on cognition-related tasks, and that they may even worse than FC baselines.
- The proposed FC-Tucker is efficient without no large-scale pretraining.
Critical weaknesses
-
The writing and presentation is unclear. The paper is difficult to follow. For example, the authors discusses and without defining them. The empirical findings, datasets, and methods are mixed in section 3, the narrative shifts between variance allocation, higher-order information, and FC preservation.
-
The foundation models the authors studied are outdated. They are limited to ROI-based input (while recent focus more on atlas-free), and they are not tuned for cognitive-related tasks. So the comparison with the FC baseline is not fair. Also, the near-zero reconstruction fidelity of BrainLM-650M and the poor HCP reconstruction results are surprising relative to previously reported BrainLM performance.
-
The authors attribute BFM underperformance to the loss of cognition-relevant third-order information. However, showing that a co-skewness-derived subspace improves FC prediction does not establish that third-order interactions are responsible for the improvement or for BFM failures.
-
The statistics used in this paper, such as third-order statistics, co-skewness analysis, and Tucker decomposition are well-established techniques. The novelty is fundamentally limited toe combination of them.
-
The baseline is not sufficient. Some other classical ML baselines, such as random orthogonal projections and ICA should also be studied. It's unknowned whether improvements arise from third-order information or more general changes in feature representation.
-
The HCP target is defined as the first principal component of 58 behavioral measures, which may not correspond to the cognitive factor used in prior studies. The authors should validate this target and clarify the comparability of their results with published benchmarks.
-
The proposed loss preserves second-order FC within a third-order-selected subspace, rather than directly preserving third-order statistics. Also, finetuning improves reconstructed FC but not the model embeddings, so it's not known whether this can produce a better generic representation.
Questions for authors
-
Is the key finding that third-order interactions contain additional cognitive information, or that a third-order-derived spatial basis improves conventional FC prediction? These are distinct claims, and the paper does not clearly distinguish them.
-
How is the Log-Cholesky metric computed for rank-deficient FC matrices when the number of ROIs exceeds the number of timepoints?