Deep Heterogeneous Contrastive Hyper-Graph Learning for In-the-Wild Context-Aware Human Activity Recognition
This addresses the challenge of multi-label activity recognition with varying sensor signals in different contexts, but it is incremental as it builds on prior graph-based methods.
The paper tackled the problem of context-aware human activity recognition by proposing a deep heterogeneous contrastive hyper-graph learning framework, which significantly outperformed state-of-the-art baselines by 5.8% to 16.7% on MCC and 3.0% to 8.4% on Macro F1 scores.
Human Activity Recognition (HAR) is a challenging, multi-label classification problem as activities may co-occur and sensor signals corresponding to the same activity may vary in different contexts (e.g., different device placements). This paper proposes a Deep Heterogeneous Contrastive Hyper-Graph Learning (DHC-HGL) framework that captures heterogenous Context-Aware HAR (CA-HAR) hypergraph properties in a message-passing and neighborhood-aggregation fashion. Prior work only explored homogeneous or shallow-node-heterogeneous graphs. DHC-HGL handles heterogeneous CA-HAR data by innovatively 1) Constructing three different types of sub-hypergraphs that are each passed through different custom HyperGraph Convolution (HGC) layers designed to handle edge-heterogeneity and 2) Adopting a contrastive loss function to ensure node-heterogeneity. In rigorous evaluation on two CA-HAR datasets, DHC-HGL significantly outperformed state-of-the-art baselines by 5.8% to 16.7% on Matthews Correlation Coefficient (MCC) and 3.0% to 8.4% on Macro F1 scores. UMAP visualizations of learned CA-HAR node embeddings are also presented to enhance model explainability.