- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies continual personalization of EEG foundation models (EFMs): subjects from several datasets arrive one at a time, and the model must adapt to each while keeping the added parameters small. Two analyses motivate the design. Layer-wise linear probing suggests shallow layers carry domain information while deeper layers carry subject information. Effective-rank measurements of full fine-tuning updates suggest that a domain-shared update needs high rank. The paper claims comparable or better accuracy than per-subject LoRA/OFT with far fewer parameters, plus ablations on the split point, adapter types, and ranks.
Critical strengths
- The problem is practical and timely. Serving a growing stream of users from heterogeneous recording setups with a single EFM is a realistic deployment scenario.
- The experiments are broad. The study covers four backbones with different architectures (bidirectional and causal, discrete-token and continuous) and three task types.
Critical weaknesses
- The central efficiency and performance claims are not supported by the paper's own evidence. For example, unaccounted replay storage overturns the efficiency claim. The abstract claims HiERA "substantially reduc[es] trainable and stored parameters." However, HiERA stores raw EEG samples in a per-domain replay buffer, and this storage is never counted. LoRA and OFT, which store nothing beyond their adapters, are charged for every parameter. Raw patient EEG is also more privacy-sensitive than adapter weights, which matters in the hospital scenario the introduction uses as motivation. Forgetting is never measured, although the method can cause it. Sec. 2.1 says previous subjects "can be directly served when their data are revisited," but all reported results test each subject immediately after adapting to it.
- The motivation analyses are confounded, and the method contradicts them. For example, the domain-probing result is trivial. In Fig. 2(a)(b), the domain-ID probe sits at 100% at every layer, not just shallow ones. So the figure shows domain information is present throughout the network, not that shallow layers are specifically domain-level. The paper's own ablations contradict its motivation. Q2/A2 argue that the domain adapter needs growing, high-rank capacity, and that fixed low-rank LoRA is "capacity-bounded." Table 4(a) shows TR rank 1 is best for the domain adapter, and larger ranks do not help. The authors themselves conclude "a low-rank transform is sufficient to capture domain-level variation" (Sec. 4.4), which directly contradicts A2. In Table 3, LoRA r=1 (16 KB, far more free parameters than the 4.56 KB TR transform) performs worse than no domain adapter at all (SEED 47.66 vs. 49.12). A model with strictly more capacity, initialized at identity and selected on validation data, underperforming no adaptation points to an optimization or protocol artifact, not a rank limitation.
- The novelty is incremental. The domain component ( with a dense TR-parameterized , motivated by OFT's sparsity) and the TR-compressed LoRA appear closely related to TLoRA (Tao et al., 2025), which the paper cites. The remaining contributions (layer split, threshold-gated adapter reuse, replay) are standard continual-learning ingredients.
Questions for authors
- It’s suggested that authors report total storage for each method in Table 2, including the replay buffer, the domain heads, and any per-subject projection layers. Does HiERA retain its advantage once these are counted? What happens without replay?
- Please report accuracy on all previously seen subjects using the final model after the full stream, and compare it to immediate post-adaptation accuracy, for HiERA and the baselines.
- How was the 56.97% REVE mean computed, given that Table 2 implies 56.63% (below full FT's 56.87%)? Please correct the 16+9 count and the "consistently improves" statement.
- How do you reconcile A2 (domain adapters need growing, high-rank capacity) with Table 4(a) (rank 1 is best) and with LoRA r=1 underperforming no adapter in Table 3?
- Can you provide within-domain subject probes and an eRank control that holds the number of optimization steps fixed?
Since there are no response from the authors, I will maintain my original score.