Graph-Based Adversarial Domain Generalization with Anatomical Correlation Knowledge for Cross-User Human Activity Recognition

2025/05/08 by Xiaozhou Ye, Ye, Xiaozhou, Kevin I‐Kai Wang +1
Computer Science · #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Context-Aware Activity Recognition Systems #FOS: Computer and information sciences #Human Pose and Action Recognition #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2506.01962

openalex publication_date 2025/05/08 · openalex created_date 2025/10/14 · openalex updated_date 2026/07/28

Abstract

Cross-user variability poses a significant challenge in sensor-based Human Activity Recognition (HAR) systems, as traditional models struggle to generalize across users due to differences in behavior, sensor placement, and data distribution. To address this, we propose GNN-ADG (Graph Neural Network with Adversarial Domain Generalization), a novel method that leverages both the strength from both the Graph Neural Networks (GNNs) and adversarial learning to achieve robust cross-user generalization. GNN-ADG models spatial relationships between sensors on different anatomical body parts, extracting three types of Anatomical Units: (1) Interconnected Units, capturing inter-relations between neighboring sensors; (2) Analogous Units, grouping sensors on symmetrical or functionally similar body parts; and (3) Lateral Units, connecting sensors based on their position to capture region-specific coordination. These units information are fused into an unified graph structure with a cyclic training strategy, dynamically integrating spatial, functional, and lateral correlations to facilitate a holistic, user-invariant representation. Information fusion mechanism of GNN-ADG occurs by iteratively cycling through edge topologies during training, allowing the model to refine its understanding of inter-sensor relationships across diverse perspectives. By representing the spatial configuration of sensors as an unified graph and incorporating adversarial learning, Information Fusion GNN-ADG effectively learns features that generalize well to unseen users without requiring target user data during training, making it practical for real-world applications.

Citations

• Deep Generative Domain Adaptation with Temporal Relation Knowledge for Cross-User Activity Recognition
• Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition
• Cross-Domain HAR: Few Shot Transfer Learning for Human Activity Recognition
• SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity Recognition
• Domain-invariant Feature Exploration for Domain Generalization
• AdaRNN: Adaptive Learning and Forecasting of Time Series
• A Brief Review of Domain Adaptation
• Learning explanations that are hard to vary
• Self-Challenging Improves Cross-Domain Generalization
• An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
• Deep Transfer Learning for Cross-domain Activity Recognition
• Generalizing to Unseen Domains via Adversarial Data Augmentation
• mixup: Beyond Empirical Risk Minimization
• Learning to Generalize: Meta-Learning for Domain Generalization
• Structured Sequence Modeling with Graph Convolutional Recurrent Networks
• DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing
• Semi-Supervised Classification with Graph Convolutional Networks
• Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables
• Unsupervised Domain Adaptation by Backpropagation
• A Comprehensive Survey on Graph Neural Networks
• A tutorial on human activity recognition using body-worn inertial sensors

Related

• Domain-Adversarial Anatomical Graph Networks for Cross-User Human Activity Recognition
• Beyond the Gates of Euclidean Space: Temporal-Discrimination-Fusions and Attention-based Graph Neural Network for Human Activity Recognition
• Adversarial Deep Feature Extraction Network for User Independent Human Activity Recognition
• TASKED: Transformer-based Adversarial learning for human activity recognition using wearable sensors via Self-KnowledgE Distillation
• Skeleton-Based Action Recognition with Spatial-Structural Graph Convolution