Papers β€Ί OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain

OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain

12 May 2025arXiv:2505.08550archive 2025-07-28

Wenzhen Yue, Yong liu, Haoxuan Li, Hao Wang, Xianghua Ying, Ruohao Guo, Bowei Xing, Ji Shi

This paper presents πŽπ‹π’π§πžπšπ«, a π₯𝐒𝐧𝐞𝐚𝐫-based multivariate time series forecasting model that operates in an 𝐨rthogonally transformed domain. Recent forecasting models typically adopt the temporal forecast (TF) paradigm, which directly encode and decode time series in the time domain. However, the entangled step-wise dependencies in series data can hinder the performance of TF. To address this, some forecasters conduct encoding and decoding in the transformed domain using fixed, dataset-independent bases (e.g., sine and cosine signals in the Fourier transform). In contrast, we utilize πŽπ«π­π‘π¨π“π«πšπ§π¬, a data-adaptive transformation based on an orthogonal matrix that diagonalizes the series' temporal Pearson correlation matrix. This approach enables more effective encoding and decoding in the decorrelated feature domain and can serve as a plug-in module to enhance existing forecasters. To enhance the representation learning for multivariate time series, we introduce a customized linear layer, 𝐍𝐨𝐫𝐦𝐋𝐒𝐧, which employs a normalized weight matrix to capture multivariate dependencies. Empirically, the NormLin module shows a surprising performance advantage over multi-head self-attention, while requiring nearly half the FLOPs. Extensive experiments on 24 benchmarks and 140 forecasting tasks demonstrate that OLinear consistently achieves state-of-the-art performance with high efficiency. Notably, as a plug-in replacement for self-attention, the NormLin module consistently enhances Transformer-based forecasters. The code and datasets are available at https://anonymous.4open.science/r/OLinear

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

jackyue1994/OLinear officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multivariate Time Series ForecastingRepresentation LearningTime SeriesTime Series Forecasting

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ADOPT

Report a problem or propose a change Β· a person checks every report against the paper or source before anything changes; decisions are listed on /corrections