发表机构
Khalifa University of Science and Technology; Aristotle University of Thessaloniki（哈利法科技大学; 亚里士多德大学塞萨洛尼基分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对野外可穿戴与智能手机情感识别的标签难题，该研究采用自监督学习结合多任务归纳式图神经网络的子图训练方法，在K-EmoPhone数据集上取得唤醒度、效价任务的准确率提升。
AI 中文摘要
基于可穿戴设备与智能手机的情感识别（WER）仍是情感计算领域的挑战性场景，原因在于野外场景下标签收集存在显著难度与偏差。被试间与被试内的高情感变异性，促使我们在有限资源学习方案中，借助自监督学习（SSL）的图掩码增强任务探索WER建模，采用图节点分类方法。训练期间我们运用子图采样方法，利用有标签与无标签数据，在多任务归纳式图神经网络架构中结合监督、半监督与自监督机制。我们在K-EmoPhone数据集上采用留组交叉验证法，针对二分类的唤醒度与效价任务开展评估：仅使用20%与25%的标签时，相比全资源设置分别取得4.3%与7.8%的平均准确率提升。模型分析揭示了SSL图增强与情感唤醒度、效价的关联，验证了自监督驱动的子图训练方法适用于野外WER的合理性。
英文摘要
Wearable and smartphone-based emotion recognition (WER) remains a challenging setting in affective computing, due to the notorious difficulty and bias associated with in-the-wild label collection. The high inter-and intra-subject emotional variability motivates us to explore WER modeling through graph node classification in a limited resources learning scheme powered by Self-Supervised Learning (SSL) graph masking augmentation tasks. We employ a subgraph sampling approach during training, utilizing labeled and unlabeled data, along with supervised, semi-supervised, and SSL mechanisms in a multi-task inductive graph neural network architecture. Our evaluations on K-EmoPhone through leave-one-group-out cross-validation in the binary arousal and valence tasks yield average accuracy gains of 4.3% and 7.8%, compared to the full resource setting, utilizing only 20% and 25% of the labels, respectively. Our model analysis sheds light on the relation of SSL graph augmentations to emotional arousal and valence and justifies the approach of SSL-driven subgraph training for in-the-wild WER.
CommentsPublished at ICASSP 2025. Copyright 2025 IEEE
DOI：10.1109/ICASSP49660.2025.10888648
