Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Unicorn: Scaling High-Dimensional Time Series Forecasting via Universal Correlation Modeling

About

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.

Haochen Yuan, Yichen Song, Yunbo Wang, Xiaokang Yang• 2026

Related benchmarks

TaskDatasetResultRank
Time Series ForecastingECL
MSE0.241
294
Financial ForecastingA-share
IC2.57
12
Financial ForecastingNASDAQ-100
IC2.38
12
Time Series ForecastingTraffic-Daily
MSE0.497
7
Time Series ForecastingCrime
MSE0.919
7
Time Series ForecastingWiki-People
MSE2.001
7
Showing 6 of 6 rows

Other info

Follow for update