融合频谱与时频图信息，提升脑机接口的脑电表征分离度。
Graph-Based Learning of Spectro-Topographical EEG Representations with Gradient Alignment for Brain-Computer Interfaces
- 用图卷积融合频率分布图和时频谱特征，捕捉多域关联。
- 引入中心损失与成对差异损失，显著提升类别间可分性。
- 通过梯度对齐缓解多源信号冲突，优化联合训练方向。
我们提出一种基于图的学习方法GEEGA，用于脑机接口中的脑电信号表征学习。该方法利用图卷积网络融合基于频率的拓扑图嵌入与时频谱特征，捕捉不同域间的关联关系。针对脑电信号时间动态性强、个体差异大的问题，GEEGA引入中心损失与成对差异损失，增强类别间可分性。同时，采用梯度对齐策略，解决多域特征与融合嵌入之间的梯度冲突，使各方向梯度趋于统一优化方向。我们在BCI-2a、CL-Drive和CLARE三个公开脑电数据集上进行了大量实验验证，全面的消融研究进一步证明了模型各组件的有效性。
原文摘要 · Abstract (English)
We present a novel graph-based learning of EEG representations with gradient alignment (GEEGA) that leverages multi-domain information to learn EEG representations for brain-computer interfaces. Our model leverages graph convolutional networks to fuse embeddings from frequency-based topographical maps and time-frequency spectrograms, capturing inter-domain relationships. GEEGA addresses the challenge of achieving high inter-class separability, which arises from the temporally dynamic and subject-sensitive nature of EEG signals by incorporating the center loss and pairwise difference loss. Additionally, GEEGA incorporates a gradient alignment strategy to resolve conflicts between gradients from different domains and the fused embeddings, ensuring that discrepancies, where gradients point in conflicting directions, are aligned toward a unified optimization direction. We validate the efficacy of our method through extensive experiments on three publicly available EEG datasets: BCI-2a, CL-Drive and CLARE. Comprehensive ablation studies further highlight the impact of various components of our model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。