4.1LGAug 2, 2025
Signals, Concepts, and Laws: Toward Universal, Explainable Time-Series ForecastingHongwei Ma, Junbin Gao, Minh-Ngoc Tran
Accurate, explainable and physically credible forecasting remains a persistent challenge for multivariate time-series whose statistical properties vary across domains. We propose DORIC, a Domain-Universal, ODE-Regularized, Interpretable-Concept Transformer for Time-Series Forecasting that generates predictions through five self-supervised, domain-agnostic concepts while enforcing differentiable residuals grounded in first-principles constraints.