- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper extends Forward-Forward learning to regression through grouped-neuron competition with Gaussian soft ordinal targets. A coarse-to-fine group schedule and a terminal head aggregate information across layers without propagating gradients between them. The layer-wise predictions are also combined to produce a final prediction and a disagreement-based uncertainty score.
Critical strengths
-
Extending local FF learning to practical regression tasks is useful. The evaluation covers six real-world datasets and multiple backbone types, and the component ablations support the proposed design.
-
The measured memory savings are substantial. In Table 13, FFR uses 1253 MB versus 4687 MB for BP-UR, with iteration time decreasing from 186.10 to 131.81 ms.
Critical weaknesses
-
The advantage over existing local-learning and distributional-regression approaches is not sufficiently established. Channel-wise competition without negative samples already appears in Papachristodoulou et al. (AAAI 2024), while Gaussian-target histogram regression was studied by Imani and White (ICML 2018), which is not discussed. The coarse-to-fine schedule and aggregation may be useful, but the FF-MSE baseline uses direct activation averaging rather than a learned local regression head. Its poor performance therefore does not establish that local MSE regression generally suffers from representation collapse. A stronger comparison with learned local MSE and distributional heads is missing.
-
The comparison with BP needs stronger evidence. The reported 98.5% figure averages BP-to-FFR error ratios rather than measuring accuracy, and it masks larger gaps on individual tasks: Tool Wear MAE increases from 7.259 to 8.388. No run-to-run variability is reported. Moreover, Table 9 measures convergence relative to each method's own minimum training criterion, not the time needed to reach the same prediction error. The reported iteration-level savings are useful, but the practical training advantage at matched accuracy, including comparison with activation-checkpointed BP, remains unclear.
Questions for authors
-
Could the authors compare FFR with learned per-layer MSE and Gaussian-target distributional heads, keeping the backbone, aggregation, and training budget matched?
-
Could the authors report repeated-run results and wall-clock time to a common validation-error target, including a memory-efficient BP baseline?
-
Goodness is computed after group normalization in Section 3.2. Without the learned affine transformation, each group's mean squared normalized activation is approximately one. How important are the affine parameters and their initialization to learning discriminative goodness scores?
-
Does the uncertainty score reliably rank prediction errors on the real-world datasets? Table 12 only evaluates synthetic tasks, and the ambiguity decomposition alone does not establish an epistemic interpretation.