SPD-MetaFormer is what you need for small-data brain decoding
Motivated by these findings, we introduce SPD-MetaFormer, an attention-free architecture built on uniformly weighted Fréchet aggregation under log-Euclidean geometry.
ProofPaper ↗
Key points
- Brain signal decoding is challenging because neural recordings are noisy and vary across individuals, while labeled data are often limited.
- Recent attention-based models on the symmetric positive definite (SPD) manifold have nevertheless achieved strong performance using covariance and connectivity representations, yet the contribution of learned token weighting remains unclear.
- We examine two representative architectures, MAtt (based on log-Euclidean geometry) and GBWAtt (based on generalized Bures--Wasserstein geometry), and find that their learned attention weights remain close to uniform after training.
- Across three EEG benchmarks, SPD-MetaFormer achieves competitive results relative to published Euclidean and manifold baselines.
Sources (1)
- [1]SPD-MetaFormer is what you need for small-data brain decodingarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 10:09 PM
Motivated by these findings, we introduce SPD-MetaFormer, an attention-free architecture built on uniformly weighted Fréchet aggregation under log-Euclidean geometry.
Brain signal decoding is challenging because neural recordings are noisy and vary across individuals, while labeled data are often limited.
Extractive summary: sentences quoted from the sources.