Self-Supervised Graph Representation Learning for In-The-Wild Wearable and Smartphone based Emotion Recognition

2026-08-23

AI Summary

为解决野外情感识别中标签收集困难的问题，采用自监督学习的图表示方法，结合子图采样和多任务归纳图神经网络架构，有效提升了情感识别准确性。

Abstract

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.

Problem

• Wearable and smartphone-based emotion recognition
• in-the-wild label collection
• inter-and intra-subject emotional variability

Innovation

• Self-Supervised Learning
• Graph Representation Learning
• Subgraph Sampling
• Wearable and Smartphone-based Emotion Recognition
• Limited Resources