用自监督图学习，在极少标签下实现穿戴设备情绪识别。
Self-Supervised Graph Representation Learning for In-The-Wild Wearable and Smartphone based Emotion Recognition
- 通过子图采样与多任务图网络融合自监督、半监督和有监督学习。
- 仅用20%-25%标签，比全量标签设置准确率提升4.3%-7.8%。
- 适合标注稀缺的真实场景情绪识别研究者参考。
基于可穿戴设备和智能手机的情绪识别（WER）在情感计算中仍具挑战性，主要源于真实场景标签收集困难且存在偏差。高个体间与个体内情绪差异促使我们探索在资源受限条件下，通过自监督学习（SSL）图掩码增强任务进行图节点分类建模。训练中采用子图采样策略，结合有标签与无标签数据，构建包含监督、半监督与自监督机制的多任务归纳式图神经网络架构。在K-EmoPhone数据集上，通过留一组外交叉验证，在二分类唤醒度与效价任务中，分别仅使用20%和25%的标签，相较于全量标签设置，平均准确率分别提升4.3%和7.8%。模型分析揭示了自监督图增强与情绪唤醒度、效价之间的关联，验证了自监督驱动子图训练在真实场景情绪识别中的有效性。
原文摘要 · Abstract (English)
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.
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。