Unicorn: Scaling High-Dimensional Time Series Forecasting via Universal Correlation Modeling
This work tackles the challenge of scaling high-dimensional time series forecasting for researchers and practitioners by enabling more effective pretraining and transfer learning across diverse datasets.
The paper introduces Unicorn, a framework for scalable, multi-dataset pretraining on high-dimensional time series, addressing the trade-off between channel-independent and channel-dependent models. Unicorn uses a latent prototype codebook to learn identity-agnostic, reusable interaction patterns, significantly outperforming state-of-the-art forecasting architectures, especially in few-shot transfer scenarios.
Modern time series architectures face a fundamental trade-off: channel-independent models scale well with increasing data volume but ignore critical inter-channel dependencies, while channel-dependent models are expressive but remain ``dimension-bounded'', struggling to generalize across heterogeneous datasets.To bridge this gap, we introduce Unicorn (Universal Correlation Network), a framework for scalable, multi-dataset pretraining on high-dimensional time series. At the core of Unicorn is a latent prototype codebook that decouples correlation modeling from specific channel identities. By projecting heterogeneous channels into a shared latent space, UniCorN learns identity-agnostic, reusable interaction patterns that transfer across domains with diverse dimensionalities and semantics. Extensive experiments show that Unicorn significantly outperforms state-of-the-art forecasting architectures, particularly in few-shot transfer scenarios, offering a scalable path toward multivariate time series foundation models.