Abstract
Deep learning for decoding EEG signals has gained traction, with many claims to state-of-the-art accuracy. However, despite the convincing benchmark performance, successful translation to real applications is limited. The frequent disconnect between performance on controlled BCI benchmarks and its lack of generalisation to practical settings indicates hidden overfitting problems. We introduce Disentangled Decoding Decomposition (D3), a weakly supervised method for training deep learning models across EEG datasets. By predicting the place in the respective trial sequence from which the input window was sampled, EEG-D3 separates latent components of brain activity, akin to non-linear ICA. We utilise a novel model architecture with fully independent sub-networks for strict interpretability. We outline a feature interpretation paradigm to contrast the component activation profiles on different datasets and inspect the associated temporal and spatial filters. The proposed method reliably separates latent components of brain activity on motor imagery data. Training downstream classifiers on an appropriate subset of these components prevents hidden overfitting caused by task-correlated artefacts, which severely affects end-to-end classifiers. We further exploit the linearly separable latent space for effective few-shot learning on sleep stage classification. The ability to distinguish genuine components of brain activity from spurious features results in models that avoid the hidden overfitting problem and generalise well to real-world applications, while requiring only minimal labelled data. With interest to the neuroscience community, the proposed method gives researchers a tool to separate individual brain processes and potentially even uncover heretofore unknown dynamics.
Abstract (translated)
深度学习在解码脑电图（EEG）信号方面取得了显著进展，并且有许多研究声称达到了最先进的准确性。然而，尽管这些方法在基准测试中的表现令人信服，但在实际应用中却效果有限。控制良好的脑机接口（BCI）基准性能与其实用场景下泛化能力的脱节表明存在隐藏的过拟合问题。为此，我们引入了分解解码分解法（Disentangled Decoding Decomposition, D3），这是一种跨EEG数据集训练深度学习模型的弱监督方法。通过预测输入窗口在相应试验序列中的位置，EEG-D3能够分离大脑活动的潜在成分，类似于非线性独立成分分析（ICA）。我们利用了一种全新的模型架构，该架构具有完全独立的子网络以严格保证可解释性。此外，我们还概述了一套特征解析范式，用于对比不同数据集上的组件激活模式，并检查相关的时间和空间滤波器。 所提出的方法能够可靠地分离运动想象数据中的大脑活动潜在成分。在下游分类器上使用这些成分的适当子集进行训练，可以防止由任务相关的伪迹造成的隐性过拟合，这种问题严重影响了端到端分类器的表现。我们进一步利用线性可分的潜在空间来进行有效的少量样本学习（few-shot learning），应用于睡眠分期分类。 区分大脑活动的真实组成部分与虚假特征的能力使模型能够避免隐藏过拟合的问题，并在实际应用中表现出良好的泛化能力，同时仅需要极少量标记数据。对于神经科学界而言，所提出的方法为研究人员提供了一种工具来分离个体的大脑过程，并有可能揭示此前未知的动力学机制。
URL
https://arxiv.org/abs/2512.13806
