量化 EEG 基础模型与信号处理嵌入中的特质—状态层级
Quantifying Trait-State Hierarchy in EEG Foundation Model and Signal Processing Embeddings
AI 导读
研究者用层级指标和 kNN 纯度在脑机接口数据集上量化 EEG 嵌入所捕捉的特质与状态特征，发现多数 EEG 特征呈宏观特质层级，即嵌入先按特质聚簇、内部再分微状态。线性探测结果表明该结构削弱状态可分性，损害 EEG 基础模型的 BCI 性能；归一化技术可将状态分类的平衡准确率提升约 10%，而下游微调会使嵌入空间从宏观特质转向宏观状态层级。
正文 · 原文
Abstract:Electroencephalography (EEG) measures brain activity through recording electrical potentials of the scalp. EEG recordings capture two distinct sets of characteristics in the signal: (1) \emph{Traits} -- information that remains relatively constant over the course of a recording session, such as subject identity, age, and sex; (2) \emph{States} -- signatures that encode responses to external stimuli, including visual, auditory, and motor information. There is limited understanding of how different EEG modeling features (signal processing and foundation models) encode state and trait characteristics. In this work, we quantify state- and trait-level features captured by EEG embeddings using a hierarchy metric and kNN purity on Brain-Computer Interface dataset trials, and find that a majority of EEG features form a macro-trait hierarchy (embeddings form trait-level clusters with micro-states within). Our linear probe results indicate that this hierarchy structure leads to suboptimal state distinguishability, negatively impacting BCI performance of EEG foundation models. To mitigate this, we explore normalization techniques that reduce trait-specific information in embeddings and provide a $\sim$ 10\% improvement in balanced accuracy for state classification. Additionally, we observe that when fine-tuning models for downstream state decoding, embedding spaces transform from macro-trait to macro-state hierarchies, which in turn lead to better state decoding.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.05652 [cs.AI] |
| (or arXiv:2611.05652v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05652 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Aditya Kommineni [view email]
[v1]
Tue, 3 Nov 2026 21:37:52 UTC (486 KB)
来源：arXiv cs.AI · arxiv.org