发表机构
Chongqing University of Technology; The Hong Kong Polytechnic University; Chongqing Polytechnic University of Electronic Technology; Affiliated Lianyungang Hospital of Xuzhou Medical University（重庆理工大学; 香港理工大学; 重庆电子工程职业技术大学; 徐州医科大学附属连云港医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出开发正则化差分图Transformer（EmoDiPyraTrans），通过自适应图递归与差分注意力建模脑电功率谱密度图，实现跨被试跨群体情绪解码，并在五个数据集上取得最优性能，同时识别出可解释的空间-频谱神经特征。
AI 中文摘要
脑电图（EEG）提供了一种非侵入性手段来捕捉与情绪相关的神经动态，然而可靠的脑电情绪解码缺乏既能泛化到未见个体和群体、又能保持神经可解释性的模型。为解决这些挑战，提出了EmoDiPyraTrans，一种开发正则化的差分图Transformer，通过自适应图递归、差分注意力和多尺度融合对按时间排序的相对功率谱密度图进行建模。该框架在三个关联层面进行了评估。首先，在SEED、FACED、MAHNOB-HCI、DEAP和DREAMER上的跨被试评估分别产生了0.928、0.645、0.714、0.617和0.671的参与者平均准确率；该模型在所有五个数据集上的准确率和正类F1分数均在被评估方法中排名第一。在七种消融协议中，差分注意力是唯一在每种情况下移除后都会降低两个指标的组件，而移除最大均值差异则全程降低了准确率。其次，DEP-EEG区分了群体内与跨群体的正性-中性解码。健康对照者内部准确率为0.802，抑郁症参与者内部为0.704，健康到抑郁迁移下为0.591。混合群体开发产生了0.581的准确率和最高的正类F1（0.498），表明仅增加群体多样性并未消除迁移差距。第三，在SEED上的通道和频率分辨分析识别出分布在前额、颞、中央和顶叶的模式，一种以alpha为中心的低到中频偏好，以及一个保持接近完整性能的六通道子集。
英文摘要
Cross subject emotion decoding from electroencephalography EEG requires representations that accommodate individual variability while preserving spatial spectral structure for interpretation. This study introduces EmoDiPyraTrans, a differential graph Transformer that integrates adaptive graph recurrence, differential attention, pyramid fusion and distribution regularization over sequential relative power spectral density graphs. Across SEED, FACED, MAHNOB HCI, DEAP and DREAMER, the model achieved the highest participant mean accuracy and positive class F1 among the evaluated methods, with accuracy and F1 both reaching 0.928 on SEED. On DEP EEG, positive versus neutral accuracy reached 0.802 within healthy controls and 0.704 within participants with depression, compared with 0.591 under healthy to depression transfer and 0.581 with mixed population development. Complementary SEED analyses identified distributed spatial weighting and an alpha centred spectral preference, while configurations averaging six channels retained near full performance. These findings link generalization assessment with model derived candidate signatures to support interpretable EEG emotion decoding, with code available at https://github.com/hdy6438/EmoDiPyraTrans.
