Conference
Open access
Sep 2026
H²SCAN: Adaptive Time Series Representation Learning via Heterogeneous Hypergraph Structure-aware Contrasts
H²SCAN is proposed, a novel augmentation-free framework that derives contrastive supervision directly from graph topology and outperforms existing methods by modeling high-order multi-domain dependencies and preserving the semantic integrity of time series data.
Biao Chen, Zi-Jie Tang, Junhua Fang et al.
· Proceedings of the Thirty-Fi... · 0 citations