- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
DualBrain is an EEG foundation model built from two components. (1) The Multi-view Joint Dynamics Encoder (MJDE) runs two parallel attention pathways per stage — Temp→Topo (temporal attention followed by electrode-axis attention) and Topo→Temp (the reverse order) — with their outputs combined by a learned, input-dependent gate, explicitly modeling both the temporal evolution of spatial patterns and the spatial distribution of temporal patterns. (2) Spherical Harmonic Positional Encoding (SHPE) represents electrode positions on the scalp sphere via real spherical harmonic bases across degrees, replacing channel IDs or Cartesian encodings. The model is pretrained with masked autoencoding on TUH (~9,246 h) and evaluated by full fine-tuning on 11 datasets spanning 7 tasks against 3 task-specific models and 6 EEG foundation models. DualBrain reports the best mean balanced accuracy (0.7368 vs 0.7134 for REVE), with the largest gains on seizure detection (+8.1 B-Acc on CHB-MIT, +5.3 on Siena), at 6.33M parameters. Ablations compare encoders (vs LaBraM/CBraMod/CSBrain), processing orders (single-path, fixed-average dual, gated dual), and positional encodings (channel ID, ACPE, 4D PE).
Critical strengths
- The ablation design is genuinely controlled and matches the claims: Table 3 compares encoder architectures under a common pretraining recipe, and Table 4 isolates the two processing orders (single-path 0.7239/0.7223, fixed dual 0.7221, gated dual 0.7368), so the dual-pathway claim is directly supported by matched comparisons rather than cross-paper numbers. For an empirical architecture paper this discipline is above the norm, and the parameter efficiency (6.33M vs REVE-Base's 69M) is a real practical benefit.
- The evaluation is broad and honestly calibrated: 11 datasets × 7 tasks, five seeds with standard deviations, reproduced baselines explicitly flagged with †, and the authors openly report where they lose (TUAB, ISRUC B-Acc) rather than only where they win.
Critical weaknesses
- The SHPE contribution is not established. Table 5 shows no positional encoding dominates per dataset (4D PE leads on TUAB, TUEV, Siena, P-MI; channel-ID on M-AT; ACPE on FACED, ISRUC), and SHPE's mean advantage over 4D PE (~1.1 points) is driven largely by a single small, high-variance dataset (M-AT: 1,707 samples, where 4D PE loses 9.3 points). SHPE's claimed montage-independence is also never directly tested — there is no cross-montage transfer experiment (e.g., pretrain at 19 channels, evaluate on denser/sparser layouts) even though that is the stated motivation. One of the two headline contributions therefore rests on a fragile aggregate.
- Novelty and gains are both incremental relative to the strength of the claims. The components recombine known ideas (axis-wise/factorized attention orderings from Crossformer/Medformer/CBraMod; spherical Fourier features as in SPE/REVE), and the average lead over REVE is concentrated on seizure datasets while many per-dataset differences fall within one seed standard deviation; Table 2 additionally mixes published numbers (from different pretraining corpora and protocols) with reproduced ones, so the "state-of-the-art" average needs a matched-corpus comparison to be meaningful.
Questions for authors
- If M-AT is excluded (or with matched seeds), does SHPE still rank first on average over the 11 datasets? Please report the average ordering with and without it.
- Can you add a direct montage-transfer evaluation to substantiate the montage-independence claim (pretrain 19-ch, fine-tune/test on denser or nonstandard montages)?
- For Table 2, which entries are reproduced under your preprocessing and splits versus copied from the original papers? A per-row provenance flag would make the average comparable.
6 comments
Response to Reviewer BwmF (2/4)
Q2: Direct test of montage independence.
Q2-1. Montage Expansion
We agree that montage independence should be tested directly, since fine-tuning lets the network adapt to each layout. To isolate montage transfer from fine-tuning, we froze each encoder pretrained on 19-channel TUEG and trained only a channel-count-independent linear head per task. We compared SHPE with Channel-ID, ACPE, and 4D-PE, keeping the encoder and head fixed when the test montage changed.
Montage expansion. We trained linear probes on the 19 electrodes shared with TUEG and tested the same frozen encoders and probes on expanded montages, without refitting: FACED (30 ch), PhysioNet-MI (64), SEED-V (62), and Siena (29). SHPE and 4D-PE compute positions from electrode coordinates, so added electrodes receive embeddings automatically. Channel-ID used a predefined embedding table covering all evaluated electrode names; added electrodes had valid IDs, but their embeddings were untrained table entries and were not learned during 19-channel pretraining or probing. This is the natural behavior of a fixed-table method on unseen electrodes, and no method received further adaptation.
| Dataset | Evaluation | Channel-ID | ACPE | 4D-PE | SHPE |
|---|---|---|---|---|---|
| FACED (30ch) | 19ch | 0.2934±0.0043 | 0.3098±0.0012 | 0.2502±0.0076 | 0.2497±0.0043 |
| Expanded | 0.2546±0.0075 | 0.2303±0.0059 | 0.2403±0.0065 | 0.2337±0.0045 | |
| Change (%) | −13.2 | −25.7 | −4.0 | −6.4 | |
| P-MI (64ch) | 19ch | 0.4306±0.0050 | 0.4137±0.0078 | 0.3543±0.0079 | 0.3442±0.0087 |
| Expanded | 0.3425±0.0023 | 0.2777±0.0045 | 0.2833±0.0040 | 0.3310±0.0052 | |
| Change (%) | −20.5 | −32.9 | −20.0 | −3.9 | |
| SEED-V (62ch) | 19ch | 0.2253±0.0019 | 0.2144±0.0040 | 0.2203±0.0022 | 0.2231±0.0010 |
| Expanded | 0.2113±0.0027 | 0.2103±0.0011 | 0.2244±0.0026 | 0.2192±0.0024 | |
| Change (%) | −6.2 | −1.9 | +1.9 | −1.8 | |
| Siena (29ch) | 19ch | 0.8562±0.0050 | 0.8446±0.0040 | 0.8479±0.0102 | 0.8282±0.0060 |
| Expanded | 0.8626±0.0118 | 0.8476±0.0032 | 0.8773±0.0012 | 0.8483±0.0022 | |
| Change (%) | +0.7 | +0.4 | +3.5 | +2.4 | |
| Avg. | Change (%) | −9.8 | −15.0 | −4.7 | −2.4 |
Linear probes were trained on the 19 channels shared with TUEG using frozen pretrained encoders, then tested on expanded channel sets (FACED: 30, P-MI: 64, SEED-V: 62, Siena: 29) without further adaptation. Each dataset reports B-Acc before and after expansion (mean ± SD), followed by relative change (%).
SHPE has the smallest average relative change (−2.4%), followed by 4D-PE (−4.7%). Compared with Channel-ID and ACPE, SHPE degrades less or improves more on all four datasets (on SEED-V the gap to ACPE is only 0.1 pp). Its advantage over 4D-PE comes from PhysioNet-MI alone (−3.9% vs. −20.0%); 4D-PE degrades less or improves more on FACED, SEED-V, and Siena. Relative change also depends on each method’s 19-channel baseline, so we report absolute B-Acc: after expansion it is highest for Channel-ID on FACED (0.2546) and PhysioNet-MI (0.3425), and for 4D-PE on SEED-V (0.2244) and Siena (0.8773). SEED-V accuracies are close to chance (0.20) and only weakly informative. With four datasets and no significance tests, we treat this as supporting evidence, not a conclusive demonstration.
Response to Reviewer BwmF (3/4)
Q2: Direct test of montage independence.
Q2-2. Electrode Dropout and Summary
Electrode dropout. Across all 11 datasets, we trained linear probes on the original electrode configurations and removed 25% of electrodes at test time, keeping encoders and probes fixed. Electrode subsets were matched across PE methods and seeds.
| Dataset | Channel-ID | ACPE | 4D-PE | SHPE |
|---|---|---|---|---|
| TUAB | 0.7878±0.0005 | 0.7981±0.0005 | 0.8072±0.0013 | 0.8100±0.0013 |
| 0.7657±0.0132 | 0.6458±0.0241 | 0.7657±0.0223 | 0.7667±0.0293 | |
| −2.8% | −19.1% | −5.1% | −5.3% | |
| TUEV | 0.5848±0.0141 | 0.5398±0.0129 | 0.5968±0.0118 | 0.5658±0.0310 |
| 0.5299±0.0353 | 0.5344±0.0261 | 0.5103±0.0515 | 0.5237±0.0515 | |
| −9.4% | −1.0% | −14.5% | −7.4% | |
| TUSZ | 0.8542±0.0025 | 0.8738±0.0042 | 0.8434±0.0025 | 0.8435±0.0027 |
| 0.8210±0.0119 | 0.8233±0.0144 | 0.7898±0.0329 | 0.7745±0.0267 | |
| −3.9% | −5.8% | −6.4% | −8.2% | |
| CHB-MIT | 0.7880±0.0103 | 0.7843±0.0356 | 0.8408±0.0077 | 0.8059±0.0272 |
| 0.7812±0.0253 | 0.7336±0.0522 | 0.7224±0.0987 | 0.7987±0.0429 | |
| −0.9% | −6.5% | −14.1% | −0.9% | |
| Siena | 0.8562±0.0050 | 0.8446±0.0040 | 0.8479±0.0102 | 0.8282±0.0060 |
| 0.8102±0.0277 | 0.8413±0.0073 | 0.8434±0.0165 | 0.8293±0.0144 | |
| −5.4% | −0.4% | −0.5% | +0.1% | |
| SEED-V | 0.2253±0.0019 | 0.2144±0.0040 | 0.2203±0.0022 | 0.2231±0.0010 |
| 0.2180±0.0024 | 0.2062±0.0018 | 0.2193±0.0063 | 0.2227±0.0053 | |
| −3.2% | −3.8% | −0.4% | −0.2% | |
| FACED | 0.2934±0.0043 | 0.3098±0.0012 | 0.2502±0.0076 | 0.2497±0.0043 |
| 0.2362±0.0152 | 0.2118±0.0147 | 0.1961±0.0109 | 0.1907±0.0139 | |
| −19.5% | −31.6% | −21.7% | −23.6% | |
| M-AT | 0.6757±0.0216 | 0.7153±0.0141 | 0.6549±0.0195 | 0.6535±0.0040 |
| 0.6306±0.0535 | 0.6618±0.0335 | 0.5556±0.0282 | 0.5549±0.0309 | |
| −6.7% | −7.5% | −15.2% | −15.1% | |
| P-MI | 0.4306±0.0050 | 0.4137±0.0078 | 0.3543±0.0079 | 0.3442±0.0087 |
| 0.3722±0.0164 | 0.3177±0.0115 | 0.2611±0.0102 | 0.3036±0.0260 | |
| −13.6% | −23.2% | −26.3% | −11.8% | |
| ISRUC | 0.7201±0.0096 | 0.6966±0.0069 | 0.7085±0.0087 | 0.6821±0.0301 |
| 0.5449±0.0274 | 0.3716±0.0461 | 0.2855±0.0335 | 0.5202±0.1245 | |
| −24.3% | −46.6% | −59.7% | −23.7% | |
| HMC | 0.6091±0.0018 | 0.6271±0.0034 | 0.6190±0.0037 | 0.6221±0.0037 |
| 0.4332±0.0567 | 0.5016±0.0173 | 0.4719±0.0261 | 0.5014±0.0386 | |
| −28.9% | −20.0% | −23.8% | −19.4% | |
| Avg. | 0.6205 | 0.6198 | 0.6130 | 0.6026 |
| 0.5585 | 0.5317 | 0.5110 | 0.5442 | |
| Avg. change | −10.8% | −15.1% | −17.1% | −10.5% |
Each dataset reports original B-Acc, B-Acc after 25% electrode dropout (mean±SD over five seeds), and relative change (%), in that order. Bold marks the smallest relative degradation per dataset.
SHPE has the smallest average relative degradation (−10.5%), nearly tied with Channel-ID (−10.8%) and below ACPE (−15.1%) and 4D-PE (−17.1%). It has the smallest degradation on 5/11 datasets (6 including the CHB-MIT tie) and the largest on TUSZ. Channel-ID has higher average absolute B-Acc (0.5585 vs. 0.5442) and naturally supports electrode removal through valid remaining IDs, so we treat this test as secondary to montage expansion. SHPE’s advantage over ACPE and 4D-PE partly reflects large ISRUC drops (−46.6% and −59.7%); excluding ISRUC, average degradation is −9.2% (SHPE), −9.4% (Channel-ID), −11.9% (ACPE), and −12.8% (4D-PE).
Summary. SHPE remains competitive in absolute B-Acc and has the smallest average relative decline under both expansion and electrode removal, though the best method varies by dataset. Given the limited evidence, we have replaced “montage-independent” with “independent of electrode names and a fixed channel set” and will add both experiments and dataset-level results to the paper.
Response to Reviewer BwmF (1/4)
Q1. If M-AT is excluded (or with matched seeds), does SHPE still rank first on average over the 11 datasets? Please report the average ordering with and without it.
Yes. SHPE still ranks first without M-AT, but its margin over 4D-PE is small and not statistically significant, and we have revised our claims accordingly.
Table:PE Performance With and Without M-AT
Values: all datasets / without M-AT. Two-sided paired t-tests across datasets, Holm-corrected over three comparisons.
Without M-AT, SHPE’s lead over 4D-PE falls from +1.13 to +0.43 pp, so M-AT contributes to the aggregate gap, but the ordering does not change. Paired t-tests give the following results. Against 4D-PE, the difference is not significant, with all 11 datasets (p = 0.162) or without M-AT (p = 0.170). Against Channel-ID, it is significant in both cases (p = 0.043 and p = 0.013). Against ACPE, it is significant with all 11 datasets (p = 0.039) but not without M-AT (p = 0.059). With only 11 datasets, we treat these tests as an approximate summary, not strong evidence, and we do not claim that SHPE significantly outperforms all alternatives on average.
The evidence supports consistency, not per-dataset superiority. SHPE ranks 1st on four datasets, 2nd on six, and 3rd on one, never last, and is never more than 1.18 pp below the best alternative on any dataset. 4D-PE ranks 3rd on three datasets and 4th on two. We now describe SHPE as competitive across heterogeneous tasks without large task-specific degradation.
Clarification of our contribution. We agree that the evidence does not show SHPE significantly outperforming all alternatives, and we will revise the abstract, introduction, and Section 4.2 to replace language implying general superiority. Our intended contribution is robustness across heterogeneous tasks, which matters for a general-purpose EEG model. SHPE attains the best mean B-Acc and mean rank (1.73 vs. 2.27 for the next best, 4D-PE), is never ranked last on any of the 11 datasets, and is never more than 1.18 pp below the best alternative on any dataset. By contrast, 4D-PE ranks 3rd or 4th on five datasets, including a large drop on M-AT (−8.13 pp). We therefore describe SHPE as competitive on every task and the most reliable on average, not as the best encoding on each benchmark. Its practical advantage, that it does not depend on a fixed channel set, is tested directly in Q2.